diff --git "a/auto_diffusers.log" "b/auto_diffusers.log"
--- "a/auto_diffusers.log"
+++ "b/auto_diffusers.log"
@@ -1529,3 +1529,4623 @@ IMPORTANT GUIDELINES:
 2025-05-29 17:05:55,607 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
 2025-05-29 17:05:55,607 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
 2025-05-29 17:05:55,607 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:38:26,490 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-29 23:38:26,490 - __main__ - DEBUG - API key found, length: 39
+2025-05-29 23:38:26,490 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-29 23:38:26,490 - auto_diffusers - DEBUG - API key length: 39
+2025-05-29 23:38:26,490 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-29 23:38:26,490 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-29 23:38:26,490 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-29 23:38:26,490 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-29 23:38:26,491 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-29 23:38:26,491 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-29 23:38:26,494 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-29 23:38:26,494 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-29 23:38:26,909 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-29 23:38:26,909 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-29 23:38:26,909 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-29 23:38:26,909 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-29 23:38:26,909 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-29 23:38:26,909 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-29 23:38:26,909 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-29 23:38:26,909 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-29 23:38:26,909 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-29 23:38:26,909 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-29 23:38:26,909 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-29 23:38:26,911 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-29 23:38:26,924 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-29 23:38:26,929 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-29 23:38:27,000 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-29 23:38:27,034 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=None socket_options=None
+2025-05-29 23:38:27,035 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12e4e1f90>
+2025-05-29 23:38:27,035 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:38:27,035 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:38:27,035 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:38:27,035 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:38:27,035 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:38:27,035 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 14:38:27 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-29 23:38:27,036 - httpx - INFO - HTTP Request: GET http://localhost:7860/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-29 23:38:27,036 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:38:27,036 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:38:27,036 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:38:27,036 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:38:27,036 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:38:27,036 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:38:27,036 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7860 local_address=None timeout=3 socket_options=None
+2025-05-29 23:38:27,037 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12f806a90>
+2025-05-29 23:38:27,037 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-29 23:38:27,037 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:38:27,037 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-29 23:38:27,037 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:38:27,037 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-29 23:38:27,042 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 14:38:27 GMT'), (b'server', b'uvicorn'), (b'content-length', b'75707'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-29 23:38:27,042 - httpx - INFO - HTTP Request: HEAD http://localhost:7860/ "HTTP/1.1 200 OK"
+2025-05-29 23:38:27,043 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-29 23:38:27,043 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:38:27,043 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:38:27,043 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:38:27,043 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:38:27,043 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:38:27,053 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-29 23:38:27,124 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12d0a56d0>
+2025-05-29 23:38:27,124 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x11a52cdd0> server_hostname='api.gradio.app' timeout=3
+2025-05-29 23:38:27,198 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12c61bd10>
+2025-05-29 23:38:27,198 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x12e4cb920> server_hostname='api.gradio.app' timeout=30
+2025-05-29 23:38:27,215 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-29 23:38:27,405 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12d0b29d0>
+2025-05-29 23:38:27,406 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:38:27,406 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:38:27,406 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:38:27,407 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:38:27,407 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:38:27,488 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11a2397d0>
+2025-05-29 23:38:27,489 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:38:27,489 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:38:27,489 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:38:27,490 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:38:27,490 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:38:27,549 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 14:38:27 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-29 23:38:27,550 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-29 23:38:27,550 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:38:27,550 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:38:27,550 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:38:27,550 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:38:27,551 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:38:27,551 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:38:27,636 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 14:38:27 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-29 23:38:27,636 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-29 23:38:27,637 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:38:27,637 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:38:27,638 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:38:27,638 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:38:27,638 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:38:27,638 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:38:28,286 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-29 23:38:28,884 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-29 23:38:42,661 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:38:42,662 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:38:42,662 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-29 23:38:42,662 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-29 23:38:42,662 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:38:42,662 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:38:42,662 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-29 23:38:42,662 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:38:42,662 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:43:46,493 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-29 23:43:46,494 - __main__ - DEBUG - API key found, length: 39
+2025-05-29 23:43:46,494 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-29 23:43:46,494 - auto_diffusers - DEBUG - API key length: 39
+2025-05-29 23:43:46,494 - auto_diffusers - DEBUG - Creating tools for Gemini
+2025-05-29 23:43:46,494 - auto_diffusers - INFO - Created 3 tools for Gemini
+2025-05-29 23:43:46,494 - auto_diffusers - INFO - Successfully configured Gemini AI model with tools
+2025-05-29 23:43:46,494 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-29 23:43:46,494 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-29 23:43:46,494 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-29 23:43:46,494 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.12.9
+2025-05-29 23:43:46,494 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-29 23:43:46,497 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-29 23:43:46,497 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-29 23:43:46,942 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-29 23:43:46,942 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-29 23:43:46,942 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-29 23:43:46,942 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.12.9', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-29 23:43:46,942 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-29 23:43:46,942 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-29 23:43:46,942 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-29 23:43:46,942 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-29 23:43:46,942 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-29 23:43:46,942 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-29 23:43:46,942 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-29 23:43:46,944 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-29 23:43:46,945 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-29 23:43:46,963 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-29 23:43:47,014 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-29 23:43:47,169 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11fad6210>
+2025-05-29 23:43:47,170 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x11f783a50> server_hostname='api.gradio.app' timeout=3
+2025-05-29 23:43:47,218 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-29 23:43:47,500 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11fad6150>
+2025-05-29 23:43:47,500 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:43:47,501 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:43:47,501 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:43:47,502 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:43:47,502 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:43:47,667 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 14:43:47 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-29 23:43:47,669 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-29 23:43:47,669 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:43:47,669 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:43:47,670 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:43:47,670 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:43:47,670 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:43:47,671 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:45:37,625 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-29 23:45:37,625 - __main__ - DEBUG - API key found, length: 39
+2025-05-29 23:45:37,625 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-29 23:45:37,625 - auto_diffusers - DEBUG - API key length: 39
+2025-05-29 23:45:37,625 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-29 23:45:37,625 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-29 23:45:37,625 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-29 23:45:37,626 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-29 23:45:37,626 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-29 23:45:37,626 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-29 23:45:37,628 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-29 23:45:37,629 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-29 23:45:38,048 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-29 23:45:38,048 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-29 23:45:38,048 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-29 23:45:38,048 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-29 23:45:38,048 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-29 23:45:38,048 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-29 23:45:38,048 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-29 23:45:38,048 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-29 23:45:38,048 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-29 23:45:38,048 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-29 23:45:38,048 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-29 23:45:38,051 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-29 23:45:38,064 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-29 23:45:38,071 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-29 23:45:38,143 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-29 23:45:38,178 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-29 23:45:38,179 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11cd37390>
+2025-05-29 23:45:38,179 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:45:38,179 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:45:38,179 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:45:38,180 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:45:38,180 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:45:38,180 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 14:45:38 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-29 23:45:38,180 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-29 23:45:38,180 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:45:38,180 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:45:38,180 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:45:38,180 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:45:38,180 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:45:38,180 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:45:38,181 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-29 23:45:38,181 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11cd18310>
+2025-05-29 23:45:38,181 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-29 23:45:38,181 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:45:38,181 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-29 23:45:38,181 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:45:38,181 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-29 23:45:38,188 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 14:45:38 GMT'), (b'server', b'uvicorn'), (b'content-length', b'113569'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-29 23:45:38,188 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-29 23:45:38,188 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-29 23:45:38,188 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:45:38,188 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:45:38,188 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:45:38,188 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:45:38,189 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:45:38,200 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-29 23:45:38,227 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11be35c50>
+2025-05-29 23:45:38,227 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x10a128ef0> server_hostname='api.gradio.app' timeout=3
+2025-05-29 23:45:38,337 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11be9f850>
+2025-05-29 23:45:38,338 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x11ccd3e30> server_hostname='api.gradio.app' timeout=30
+2025-05-29 23:45:38,349 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-29 23:45:38,503 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11a95c850>
+2025-05-29 23:45:38,503 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:45:38,503 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:45:38,503 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:45:38,503 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:45:38,503 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:45:38,611 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11af28e50>
+2025-05-29 23:45:38,611 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:45:38,611 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:45:38,611 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:45:38,611 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:45:38,611 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:45:38,641 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 14:45:38 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-29 23:45:38,642 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-29 23:45:38,642 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:45:38,642 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:45:38,642 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:45:38,642 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:45:38,642 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:45:38,642 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:45:38,750 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 14:45:38 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-29 23:45:38,750 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-29 23:45:38,750 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:45:38,751 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:45:38,751 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:45:38,751 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:45:38,751 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:45:38,751 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:45:39,336 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-29 23:45:39,554 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-29 23:45:56,868 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:45:56,868 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:45:56,868 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-29 23:45:56,869 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-29 23:45:56,869 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:45:56,869 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:45:56,869 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-29 23:45:56,869 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:45:56,869 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:46:55,462 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:46:55,462 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:46:55,462 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-29 23:46:55,462 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:46:55,462 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:46:55,462 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-29 23:46:55,462 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:46:55,462 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:47:01,722 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:47:01,722 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:47:01,722 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM
+2025-05-29 23:47:01,723 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:47:01,723 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:47:01,723 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-29 23:47:01,723 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:47:01,723 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:47:01,774 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:47:01,775 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:47:01,775 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 32.0GB VRAM
+2025-05-29 23:47:01,775 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:47:01,775 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:47:01,775 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-29 23:47:01,775 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:47:01,775 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:48:44,089 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-29 23:48:44,089 - __main__ - DEBUG - API key found, length: 39
+2025-05-29 23:48:44,089 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-29 23:48:44,089 - auto_diffusers - DEBUG - API key length: 39
+2025-05-29 23:48:44,089 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-29 23:48:44,089 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-29 23:48:44,089 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-29 23:48:44,089 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-29 23:48:44,089 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-29 23:48:44,089 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-29 23:48:44,092 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-29 23:48:44,092 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-29 23:48:44,496 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-29 23:48:44,497 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-29 23:48:44,497 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-29 23:48:44,497 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-29 23:48:44,497 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-29 23:48:44,497 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-29 23:48:44,497 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-29 23:48:44,497 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-29 23:48:44,497 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-29 23:48:44,497 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-29 23:48:44,497 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-29 23:48:44,499 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-29 23:48:44,512 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-29 23:48:44,517 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-29 23:48:44,590 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-29 23:48:44,625 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-29 23:48:44,626 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x127d00850>
+2025-05-29 23:48:44,626 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:48:44,626 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:48:44,626 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:48:44,626 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:48:44,627 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:48:44,627 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 14:48:44 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-29 23:48:44,627 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-29 23:48:44,627 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:48:44,627 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:48:44,627 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:48:44,627 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:48:44,627 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:48:44,627 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:48:44,628 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-29 23:48:44,628 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x127d3bd10>
+2025-05-29 23:48:44,628 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-29 23:48:44,628 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:48:44,629 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-29 23:48:44,629 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:48:44,629 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-29 23:48:44,635 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 14:48:44 GMT'), (b'server', b'uvicorn'), (b'content-length', b'113500'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-29 23:48:44,635 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-29 23:48:44,635 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-29 23:48:44,635 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:48:44,635 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:48:44,635 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:48:44,636 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:48:44,636 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:48:44,647 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-29 23:48:44,676 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1267846d0>
+2025-05-29 23:48:44,676 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x114330e60> server_hostname='api.gradio.app' timeout=3
+2025-05-29 23:48:44,796 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x124fb78d0>
+2025-05-29 23:48:44,796 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x127ccfda0> server_hostname='api.gradio.app' timeout=30
+2025-05-29 23:48:44,801 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-29 23:48:44,957 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x125c31d90>
+2025-05-29 23:48:44,958 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:48:44,958 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:48:44,958 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:48:44,958 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:48:44,958 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:48:45,095 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x122dce550>
+2025-05-29 23:48:45,096 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:48:45,096 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:48:45,096 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:48:45,096 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:48:45,096 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:48:45,100 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 14:48:45 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-29 23:48:45,100 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-29 23:48:45,101 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:48:45,101 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:48:45,101 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:48:45,101 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:48:45,101 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:48:45,101 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:48:45,247 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 14:48:45 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-29 23:48:45,248 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-29 23:48:45,248 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:48:45,249 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:48:45,249 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:48:45,249 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:48:45,250 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:48:45,250 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:48:45,928 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-29 23:48:46,505 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-29 23:48:47,065 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:48:47,065 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:48:47,065 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-29 23:48:47,065 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-29 23:48:47,065 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:48:47,065 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:48:47,065 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-29 23:48:47,065 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:48:47,065 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:50:45,671 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-29 23:50:45,671 - __main__ - DEBUG - API key found, length: 39
+2025-05-29 23:50:45,671 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-29 23:50:45,671 - auto_diffusers - DEBUG - API key length: 39
+2025-05-29 23:50:45,671 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-29 23:50:45,671 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-29 23:50:45,671 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-29 23:50:45,671 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-29 23:50:45,671 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-29 23:50:45,671 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-29 23:50:45,675 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-29 23:50:45,675 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-29 23:50:46,156 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-29 23:50:46,156 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-29 23:50:46,156 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-29 23:50:46,156 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-29 23:50:46,156 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-29 23:50:46,156 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-29 23:50:46,156 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-29 23:50:46,156 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-29 23:50:46,156 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-29 23:50:46,156 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-29 23:50:46,156 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-29 23:50:46,158 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-29 23:50:46,172 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-29 23:50:46,178 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-29 23:50:46,266 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-29 23:50:46,302 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-29 23:50:46,303 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x139f68a50>
+2025-05-29 23:50:46,303 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:50:46,303 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:50:46,303 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:50:46,303 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:50:46,304 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:50:46,304 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 14:50:46 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-29 23:50:46,304 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-29 23:50:46,304 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:50:46,304 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:50:46,304 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:50:46,304 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:50:46,304 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:50:46,305 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:50:46,305 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-29 23:50:46,305 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x13e779350>
+2025-05-29 23:50:46,305 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-29 23:50:46,306 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:50:46,306 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-29 23:50:46,306 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:50:46,306 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-29 23:50:46,312 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 14:50:46 GMT'), (b'server', b'uvicorn'), (b'content-length', b'111775'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-29 23:50:46,312 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-29 23:50:46,313 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-29 23:50:46,313 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:50:46,313 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:50:46,313 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:50:46,313 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:50:46,313 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:50:46,324 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-29 23:50:46,376 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x139f2b110>
+2025-05-29 23:50:46,376 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x139c91ac0> server_hostname='api.gradio.app' timeout=3
+2025-05-29 23:50:46,463 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x13e7d6050>
+2025-05-29 23:50:46,464 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x13bbd3da0> server_hostname='api.gradio.app' timeout=30
+2025-05-29 23:50:46,471 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-29 23:50:46,648 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x13e82cb90>
+2025-05-29 23:50:46,648 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:50:46,648 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:50:46,648 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:50:46,649 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:50:46,649 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:50:46,744 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12f77fb90>
+2025-05-29 23:50:46,744 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:50:46,744 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:50:46,744 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:50:46,744 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:50:46,744 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:50:46,786 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 14:50:46 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-29 23:50:46,786 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-29 23:50:46,786 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:50:46,786 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:50:46,786 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:50:46,786 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:50:46,786 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:50:46,787 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:50:46,885 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 14:50:46 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-29 23:50:46,885 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-29 23:50:46,885 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:50:46,885 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:50:46,885 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:50:46,885 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:50:46,886 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:50:46,886 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:50:47,013 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:50:47,013 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:50:47,014 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-29 23:50:47,014 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-29 23:50:47,014 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:50:47,014 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:50:47,014 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-29 23:50:47,014 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:50:47,014 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:50:47,517 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-29 23:50:47,739 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-29 23:54:53,253 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-29 23:54:53,253 - __main__ - DEBUG - API key found, length: 39
+2025-05-29 23:54:53,253 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-29 23:54:53,253 - auto_diffusers - DEBUG - API key length: 39
+2025-05-29 23:54:53,253 - auto_diffusers - DEBUG - Creating tools for Gemini
+2025-05-29 23:54:53,253 - auto_diffusers - INFO - Created 3 tools for Gemini
+2025-05-29 23:54:53,253 - auto_diffusers - INFO - Successfully configured Gemini AI model with tools
+2025-05-29 23:54:53,253 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-29 23:54:53,253 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-29 23:54:53,253 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-29 23:54:53,253 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.12.9
+2025-05-29 23:54:53,253 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-29 23:54:53,258 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-29 23:54:53,258 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-29 23:54:53,724 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-29 23:54:53,724 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-29 23:54:53,724 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-29 23:54:53,724 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.12.9', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-29 23:54:53,724 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-29 23:54:53,724 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-29 23:54:53,724 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-29 23:54:53,724 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-29 23:54:53,724 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-29 23:54:53,724 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-29 23:54:53,724 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-29 23:54:53,726 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-29 23:54:53,734 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-29 23:54:53,740 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-29 23:54:53,988 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-29 23:54:53,989 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1278f5730>
+2025-05-29 23:54:53,989 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x1278839d0> server_hostname='api.gradio.app' timeout=3
+2025-05-29 23:54:54,271 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x127a97740>
+2025-05-29 23:54:54,271 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:54:54,272 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:54:54,272 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:54:54,272 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:54:54,272 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:54:54,415 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 14:54:54 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-29 23:54:54,416 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-29 23:54:54,416 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:54:54,416 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:54:54,416 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:54:54,416 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:54:54,416 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:54:54,416 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:55:03,477 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-29 23:55:03,477 - __main__ - DEBUG - API key found, length: 39
+2025-05-29 23:55:03,477 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-29 23:55:03,477 - auto_diffusers - DEBUG - API key length: 39
+2025-05-29 23:55:03,477 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-29 23:55:03,477 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-29 23:55:03,477 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-29 23:55:03,477 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-29 23:55:03,477 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-29 23:55:03,477 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-29 23:55:03,481 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-29 23:55:03,481 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-29 23:55:03,929 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-29 23:55:03,929 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-29 23:55:03,929 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-29 23:55:03,929 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-29 23:55:03,929 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-29 23:55:03,929 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-29 23:55:03,929 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-29 23:55:03,929 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-29 23:55:03,929 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-29 23:55:03,929 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-29 23:55:03,929 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-29 23:55:03,931 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-29 23:55:03,944 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-29 23:55:03,950 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-29 23:55:04,086 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1270ac610>
+2025-05-29 23:55:04,086 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x115830e60> server_hostname='api.gradio.app' timeout=3
+2025-05-29 23:55:04,359 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x127046cd0>
+2025-05-29 23:55:04,359 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:55:04,360 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:55:04,360 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:55:04,360 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:55:04,360 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:55:04,410 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-29 23:55:04,498 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 14:55:04 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-29 23:55:04,500 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-29 23:55:04,500 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:55:04,501 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:55:04,501 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:55:04,501 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:55:04,501 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:55:04,502 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:55:14,094 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-29 23:55:14,094 - __main__ - DEBUG - API key found, length: 39
+2025-05-29 23:55:14,094 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-29 23:55:14,094 - auto_diffusers - DEBUG - API key length: 39
+2025-05-29 23:55:14,094 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-29 23:55:14,094 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-29 23:55:14,094 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-29 23:55:14,094 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-29 23:55:14,094 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-29 23:55:14,094 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-29 23:55:14,097 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-29 23:55:14,098 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-29 23:55:14,515 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-29 23:55:14,515 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-29 23:55:14,515 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-29 23:55:14,516 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-29 23:55:14,516 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-29 23:55:14,516 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-29 23:55:14,516 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-29 23:55:14,516 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-29 23:55:14,516 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-29 23:55:14,516 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-29 23:55:14,516 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-29 23:55:14,518 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-29 23:55:14,530 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-29 23:55:14,536 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-29 23:55:14,678 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x113b38a90>
+2025-05-29 23:55:14,679 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x124a91a30> server_hostname='api.gradio.app' timeout=3
+2025-05-29 23:55:14,759 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-29 23:55:14,964 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12438cd50>
+2025-05-29 23:55:14,965 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:55:14,965 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:55:14,965 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:55:14,965 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:55:14,965 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:55:15,107 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 14:55:15 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-29 23:55:15,108 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-29 23:55:15,108 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:55:15,108 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:55:15,108 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:55:15,108 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:55:15,108 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:55:15,109 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:55:43,365 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-29 23:55:43,366 - __main__ - DEBUG - API key found, length: 39
+2025-05-29 23:55:43,366 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-29 23:55:43,366 - auto_diffusers - DEBUG - API key length: 39
+2025-05-29 23:55:43,366 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-29 23:55:43,366 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-29 23:55:43,366 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-29 23:55:43,366 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-29 23:55:43,366 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-29 23:55:43,366 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-29 23:55:43,369 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-29 23:55:43,369 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-29 23:55:43,790 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-29 23:55:43,790 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-29 23:55:43,790 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-29 23:55:43,790 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-29 23:55:43,790 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-29 23:55:43,790 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-29 23:55:43,790 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-29 23:55:43,790 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-29 23:55:43,790 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-29 23:55:43,790 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-29 23:55:43,790 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-29 23:55:43,792 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-29 23:55:43,804 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-29 23:55:43,811 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-29 23:55:43,947 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1313a3610>
+2025-05-29 23:55:43,947 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x120530e60> server_hostname='api.gradio.app' timeout=3
+2025-05-29 23:55:44,023 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-29 23:55:44,220 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x125d01350>
+2025-05-29 23:55:44,220 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:55:44,221 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:55:44,221 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:55:44,221 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:55:44,221 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:55:44,358 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 14:55:44 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-29 23:55:44,359 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-29 23:55:44,359 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:55:44,359 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:55:44,359 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:55:44,359 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:55:44,359 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:55:44,359 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:56:37,153 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-29 23:56:37,153 - __main__ - DEBUG - API key found, length: 39
+2025-05-29 23:56:37,153 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-29 23:56:37,153 - auto_diffusers - DEBUG - API key length: 39
+2025-05-29 23:56:37,153 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-29 23:56:37,153 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-29 23:56:37,153 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-29 23:56:37,153 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-29 23:56:37,153 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-29 23:56:37,153 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-29 23:56:37,156 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-29 23:56:37,156 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-29 23:56:37,560 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-29 23:56:37,560 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-29 23:56:37,560 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-29 23:56:37,560 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-29 23:56:37,560 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-29 23:56:37,560 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-29 23:56:37,560 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-29 23:56:37,560 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-29 23:56:37,560 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-29 23:56:37,560 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-29 23:56:37,560 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-29 23:56:37,562 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-29 23:56:37,575 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-29 23:56:37,581 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-29 23:56:37,658 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-29 23:56:37,691 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-29 23:56:37,692 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x127f39350>
+2025-05-29 23:56:37,692 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:56:37,692 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:56:37,692 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:56:37,692 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:56:37,692 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:56:37,692 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 14:56:37 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-29 23:56:37,693 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-29 23:56:37,693 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:56:37,693 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:56:37,693 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:56:37,693 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:56:37,693 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:56:37,693 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:56:37,693 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-29 23:56:37,694 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x159013f10>
+2025-05-29 23:56:37,694 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-29 23:56:37,694 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:56:37,694 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-29 23:56:37,694 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:56:37,694 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-29 23:56:37,700 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 14:56:37 GMT'), (b'server', b'uvicorn'), (b'content-length', b'106594'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-29 23:56:37,700 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-29 23:56:37,700 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-29 23:56:37,700 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:56:37,700 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:56:37,700 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:56:37,701 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:56:37,701 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:56:37,711 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-29 23:56:37,874 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-29 23:56:37,902 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1278a3150>
+2025-05-29 23:56:37,902 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x115230e60> server_hostname='api.gradio.app' timeout=3
+2025-05-29 23:56:37,903 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1238c7a10>
+2025-05-29 23:56:37,903 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x127edbd10> server_hostname='api.gradio.app' timeout=30
+2025-05-29 23:56:38,185 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1278dcb50>
+2025-05-29 23:56:38,185 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:56:38,185 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:56:38,185 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:56:38,185 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:56:38,185 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:56:38,187 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x127847c10>
+2025-05-29 23:56:38,187 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-29 23:56:38,187 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-29 23:56:38,187 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-29 23:56:38,187 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-29 23:56:38,187 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-29 23:56:38,330 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 14:56:38 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-29 23:56:38,330 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-29 23:56:38,331 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:56:38,331 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 14:56:38 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-29 23:56:38,331 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:56:38,332 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-29 23:56:38,332 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:56:38,332 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-29 23:56:38,332 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:56:38,333 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:56:38,333 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-29 23:56:38,333 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-29 23:56:38,333 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:56:38,333 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-29 23:56:38,334 - httpcore.connection - DEBUG - close.started
+2025-05-29 23:56:38,334 - httpcore.connection - DEBUG - close.complete
+2025-05-29 23:56:39,018 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-29 23:56:39,237 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-29 23:56:42,308 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:56:42,308 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:56:42,308 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-29 23:56:42,308 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-29 23:56:42,308 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:56:42,308 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-29 23:56:42,308 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-29 23:56:42,308 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-29 23:56:42,308 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:00:01,476 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:00:01,476 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:00:01,476 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:00:01,476 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:00:01,476 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:00:01,476 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:00:01,476 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:00:01,476 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:00:01,476 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:00:01,476 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:00:01,480 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:00:01,481 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:00:01,916 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:00:01,916 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:00:01,916 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:00:01,916 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:00:01,916 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:00:01,916 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:00:01,916 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:00:01,916 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:00:01,916 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:00:01,916 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:00:01,916 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:00:01,918 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:00:01,930 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:00:01,936 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:00:02,010 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:00:02,048 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:00:02,049 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12a552fd0>
+2025-05-30 00:00:02,049 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:00:02,049 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:00:02,049 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:00:02,049 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:00:02,049 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:00:02,050 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:00:02 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:00:02,050 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:00:02,050 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:00:02,050 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:00:02,050 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:00:02,050 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:00:02,050 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:00:02,050 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:00:02,050 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:00:02,052 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12b234a10>
+2025-05-30 00:00:02,052 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:00:02,052 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:00:02,052 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:00:02,052 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:00:02,052 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:00:02,058 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:00:02 GMT'), (b'server', b'uvicorn'), (b'content-length', b'109706'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:00:02,058 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:00:02,058 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:00:02,058 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:00:02,058 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:00:02,058 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:00:02,058 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:00:02,058 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:00:02,069 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:00:02,138 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12915e7d0>
+2025-05-30 00:00:02,138 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x10ed24f80> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:00:02,207 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x129a80250>
+2025-05-30 00:00:02,207 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x12b1d7f50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:00:02,293 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:00:02,420 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12b1539d0>
+2025-05-30 00:00:02,420 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:00:02,420 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:00:02,421 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:00:02,421 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:00:02,421 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:00:02,486 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12a091310>
+2025-05-30 00:00:02,486 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:00:02,487 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:00:02,487 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:00:02,487 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:00:02,487 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:00:02,561 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:00:02 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:00:02,562 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:00:02,563 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:00:02,563 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:00:02,564 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:00:02,564 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:00:02,564 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:00:02,565 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:00:02,627 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:00:02 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:00:02,629 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:00:02,630 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:00:02,630 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:00:02,630 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:00:02,631 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:00:02,635 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:00:02,636 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:00:02,709 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:00:02,709 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:00:02,709 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:00:02,710 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:00:02,710 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:00:02,710 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:00:02,710 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:00:02,710 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:00:02,710 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:00:03,267 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:00:03,490 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:04:08,649 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:04:08,650 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:04:08,650 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:04:08,650 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:04:08,650 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:04:08,650 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:04:08,650 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:04:08,650 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:04:08,650 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:04:08,650 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:04:08,653 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:04:08,654 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:04:09,095 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:04:09,095 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:04:09,095 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:04:09,095 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:04:09,095 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:04:09,095 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:04:09,095 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:04:09,095 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:04:09,095 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:04:09,095 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:04:09,096 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:04:09,098 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:04:09,119 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:04:09,125 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:04:09,205 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:04:09,239 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:04:09,240 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x163ee28d0>
+2025-05-30 00:04:09,240 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:04:09,240 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:04:09,240 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:04:09,240 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:04:09,240 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:04:09,240 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:04:09 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:04:09,241 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:04:09,241 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:04:09,241 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:04:09,241 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:04:09,241 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:04:09,241 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:04:09,241 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:04:09,241 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:04:09,242 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x166a12a90>
+2025-05-30 00:04:09,242 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:04:09,242 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:04:09,242 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:04:09,242 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:04:09,242 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:04:09,248 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:04:09 GMT'), (b'server', b'uvicorn'), (b'content-length', b'107757'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:04:09,248 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:04:09,248 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:04:09,248 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:04:09,248 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:04:09,248 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:04:09,248 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:04:09,248 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:04:09,259 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:04:09,286 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x162aa1f90>
+2025-05-30 00:04:09,286 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x120824f80> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:04:09,399 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x163c1d7d0>
+2025-05-30 00:04:09,399 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x163ed3f50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:04:09,404 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:04:09,567 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x162309890>
+2025-05-30 00:04:09,567 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:04:09,567 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:04:09,567 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:04:09,567 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:04:09,567 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:04:09,678 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x162abca50>
+2025-05-30 00:04:09,678 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:04:09,678 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:04:09,678 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:04:09,678 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:04:09,678 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:04:09,710 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:04:09 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:04:09,710 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:04:09,710 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:04:09,710 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:04:09,710 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:04:09,710 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:04:09,710 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:04:09,711 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:04:09,820 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:04:09 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:04:09,820 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:04:09,820 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:04:09,820 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:04:09,820 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:04:09,820 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:04:09,820 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:04:09,820 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:04:10,304 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:04:10,304 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:04:10,305 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:04:10,305 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:04:10,305 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:04:10,305 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:04:10,305 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:04:10,305 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:04:10,305 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:04:10,453 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:04:10,668 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:05:09,731 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:05:09,732 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:05:09,732 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:05:09,732 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:05:09,732 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:05:09,732 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:05:09,732 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:05:09,732 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:05:09,732 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:05:09,732 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:05:09,736 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:05:09,736 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:05:10,155 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:05:10,155 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:05:10,155 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:05:10,155 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:05:10,155 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:05:10,155 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:05:10,155 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:05:10,155 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:05:10,155 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:05:10,155 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:05:10,155 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:05:10,157 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:05:10,170 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:05:10,177 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:05:10,271 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:05:10,302 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:05:10,303 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12b4ea090>
+2025-05-30 00:05:10,303 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:05:10,303 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:05:10,303 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:05:10,303 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:05:10,304 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:05:10,304 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:05:10 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:05:10,304 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:05:10,304 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:05:10,304 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:05:10,304 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:05:10,304 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:05:10,304 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:05:10,304 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:05:10,304 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:05:10,305 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12b45c090>
+2025-05-30 00:05:10,305 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:05:10,305 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:05:10,305 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:05:10,305 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:05:10,305 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:05:10,311 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:05:10 GMT'), (b'server', b'uvicorn'), (b'content-length', b'107689'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:05:10,311 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:05:10,311 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:05:10,311 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:05:10,311 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:05:10,311 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:05:10,311 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:05:10,311 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:05:10,315 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12a1556d0>
+2025-05-30 00:05:10,315 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x12948d760> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:05:10,322 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:05:10,453 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:05:10,464 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11e21e610>
+2025-05-30 00:05:10,464 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x12b5d3f50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:05:10,591 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12a122b90>
+2025-05-30 00:05:10,591 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:05:10,592 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:05:10,592 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:05:10,592 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:05:10,592 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:05:10,732 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:05:10 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:05:10,733 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:05:10,733 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:05:10,734 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:05:10,734 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:05:10,734 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:05:10,734 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:05:10,735 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:05:10,750 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x128ac0610>
+2025-05-30 00:05:10,751 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:05:10,751 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:05:10,751 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:05:10,751 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:05:10,751 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:05:10,896 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:05:10 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:05:10,897 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:05:10,898 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:05:10,898 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:05:10,898 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:05:10,898 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:05:10,899 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:05:10,899 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:05:11,318 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:05:11,318 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:05:11,318 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:05:11,318 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:05:11,318 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:05:11,318 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:05:11,318 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:05:11,318 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:05:11,318 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:05:11,467 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:05:11,688 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:06:35,442 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:06:35,442 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:06:35,442 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:06:35,442 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:06:35,442 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:06:35,442 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:06:35,442 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:06:35,442 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:06:35,442 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:06:35,442 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:06:35,446 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:06:35,446 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:06:35,858 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:06:35,858 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:06:35,858 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:06:35,858 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:06:35,858 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:06:35,858 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:06:35,858 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:06:35,858 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:06:35,858 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:06:35,858 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:06:35,858 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:06:35,860 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:06:35,873 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:06:35,878 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:06:35,949 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:06:35,984 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:06:35,984 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11faee9d0>
+2025-05-30 00:06:35,985 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:06:35,985 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:06:35,985 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:06:35,985 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:06:35,985 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:06:35,985 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:06:35 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:06:35,985 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:06:35,985 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:06:35,985 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:06:35,986 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:06:35,986 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:06:35,986 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:06:35,986 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:06:35,986 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:06:35,986 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11fc12790>
+2025-05-30 00:06:35,986 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:06:35,987 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:06:35,987 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:06:35,987 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:06:35,987 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:06:35,993 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:06:35 GMT'), (b'server', b'uvicorn'), (b'content-length', b'107788'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:06:35,993 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:06:35,993 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:06:35,993 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:06:35,993 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:06:35,993 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:06:35,993 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:06:35,993 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:06:36,003 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:06:36,066 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11d31e7d0>
+2025-05-30 00:06:36,066 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x11dc89760> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:06:36,146 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11fc9d050>
+2025-05-30 00:06:36,146 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x11fad3f50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:06:36,188 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:06:36,349 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11fa44d10>
+2025-05-30 00:06:36,350 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:06:36,351 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:06:36,351 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:06:36,351 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:06:36,351 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:06:36,439 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11d92f790>
+2025-05-30 00:06:36,441 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:06:36,443 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:06:36,444 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:06:36,444 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:06:36,444 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:06:36,493 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:06:36 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:06:36,494 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:06:36,494 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:06:36,495 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:06:36,495 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:06:36,495 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:06:36,495 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:06:36,496 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:06:36,588 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:06:36 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:06:36,589 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:06:36,589 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:06:36,590 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:06:36,590 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:06:36,590 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:06:36,590 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:06:36,590 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:06:37,231 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:06:37,458 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:06:55,393 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:06:55,393 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:06:55,393 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:06:55,393 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:06:55,393 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:06:55,393 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:06:55,393 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:06:55,393 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:06:55,394 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:08:02,686 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:08:02,686 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:08:02,686 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:08:02,686 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:08:02,686 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:08:02,686 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:08:02,687 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:08:02,687 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:08:02,687 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:08:02,687 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:08:02,690 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:08:02,690 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:08:03,143 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:08:03,143 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:08:03,144 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:08:03,144 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:08:03,144 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:08:03,144 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:08:03,144 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:08:03,144 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:08:03,144 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:08:03,144 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:08:03,144 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:08:03,146 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:08:03,160 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:08:03,166 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:08:03,239 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:08:03,273 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:08:03,274 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11edb6510>
+2025-05-30 00:08:03,274 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:08:03,274 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:08:03,275 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:08:03,275 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:08:03,275 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:08:03,275 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:08:03 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:08:03,275 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:08:03,275 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:08:03,275 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:08:03,275 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:08:03,275 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:08:03,275 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:08:03,275 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:08:03,276 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:08:03,276 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11fe16610>
+2025-05-30 00:08:03,276 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:08:03,276 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:08:03,276 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:08:03,276 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:08:03,276 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:08:03,283 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:08:03 GMT'), (b'server', b'uvicorn'), (b'content-length', b'107135'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:08:03,283 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:08:03,283 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:08:03,283 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:08:03,283 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:08:03,283 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:08:03,283 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:08:03,283 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:08:03,295 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:08:03,328 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11ed98f10>
+2025-05-30 00:08:03,328 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x10c924f80> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:08:03,436 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11b53a290>
+2025-05-30 00:08:03,436 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x11fccff50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:08:03,443 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:08:03,617 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11fc403d0>
+2025-05-30 00:08:03,618 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:08:03,618 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:08:03,619 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:08:03,619 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:08:03,619 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:08:03,715 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11b5fb5d0>
+2025-05-30 00:08:03,715 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:08:03,716 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:08:03,716 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:08:03,716 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:08:03,716 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:08:03,763 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:08:03 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:08:03,763 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:08:03,763 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:08:03,763 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:08:03,763 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:08:03,763 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:08:03,763 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:08:03,763 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:08:03,855 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:08:03 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:08:03,856 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:08:03,856 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:08:03,856 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:08:03,856 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:08:03,856 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:08:03,856 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:08:03,856 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:08:04,087 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:08:04,087 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:08:04,087 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:08:04,087 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:08:04,087 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:08:04,087 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:08:04,087 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:08:04,087 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:08:04,087 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:08:04,452 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:08:04,684 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:12:12,860 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:12:12,860 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:12:12,860 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:12:12,860 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:12:12,860 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:12:12,860 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:12:12,860 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:12:12,860 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:12:12,860 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:12:12,860 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:12:12,864 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:12:12,865 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:12:13,341 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:12:13,341 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:12:13,341 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:12:13,341 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:12:13,341 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:12:13,342 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:12:13,342 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:12:13,342 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:12:13,342 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:12:13,342 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:12:13,342 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:12:13,344 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:12:13,358 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:12:13,365 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:12:13,448 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:12:13,481 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:12:13,482 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x301e7d990>
+2025-05-30 00:12:13,482 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:12:13,482 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:12:13,483 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:12:13,483 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:12:13,483 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:12:13,483 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:12:13 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:12:13,483 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:12:13,483 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:12:13,483 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:12:13,483 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:12:13,483 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:12:13,483 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:12:13,483 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:12:13,484 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:12:13,484 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x308aa25d0>
+2025-05-30 00:12:13,484 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:12:13,484 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:12:13,484 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:12:13,484 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:12:13,484 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:12:13,490 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:12:13 GMT'), (b'server', b'uvicorn'), (b'content-length', b'106328'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:12:13,491 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:12:13,491 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:12:13,491 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:12:13,491 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:12:13,491 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:12:13,491 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:12:13,491 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:12:13,502 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:12:13,604 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x300b5bf90>
+2025-05-30 00:12:13,604 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x125b24f80> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:12:13,643 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x16fec0a90>
+2025-05-30 00:12:13,643 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x301fcbf50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:12:13,650 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:12:13,887 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x300b7b310>
+2025-05-30 00:12:13,888 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:12:13,888 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:12:13,888 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:12:13,888 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:12:13,888 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:12:13,919 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x30017a850>
+2025-05-30 00:12:13,919 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:12:13,919 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:12:13,919 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:12:13,919 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:12:13,919 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:12:14,033 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:12:14 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:12:14,033 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:12:14,034 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:12:14,034 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:12:14,034 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:12:14,034 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:12:14,034 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:12:14,034 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:12:14,060 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:12:14 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:12:14,061 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:12:14,061 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:12:14,061 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:12:14,062 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:12:14,062 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:12:14,062 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:12:14,062 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:12:14,141 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:12:14,141 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:12:14,141 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:12:14,141 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:12:14,141 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:12:14,142 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:12:14,142 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:12:14,142 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:12:14,142 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:12:14,655 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:12:14,884 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:13:17,944 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:13:17,944 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:13:17,944 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:13:17,944 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:13:17,944 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:13:17,944 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:13:17,944 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:13:17,944 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:13:17,944 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:13:17,944 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:13:17,948 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:13:17,948 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:13:18,354 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:13:18,354 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:13:18,354 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:13:18,354 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:13:18,354 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:13:18,354 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:13:18,354 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:13:18,354 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:13:18,354 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:13:18,354 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:13:18,354 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:13:18,356 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:13:18,369 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:13:18,375 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:13:18,445 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:13:18,480 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:13:18,481 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12786abd0>
+2025-05-30 00:13:18,481 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:13:18,481 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:13:18,481 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:13:18,481 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:13:18,481 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:13:18,481 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:13:18 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:13:18,482 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:13:18,482 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:13:18,482 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:13:18,482 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:13:18,482 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:13:18,482 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:13:18,482 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:13:18,482 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:13:18,482 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12786b490>
+2025-05-30 00:13:18,483 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:13:18,483 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:13:18,483 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:13:18,483 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:13:18,483 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:13:18,489 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:13:18 GMT'), (b'server', b'uvicorn'), (b'content-length', b'106650'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:13:18,489 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:13:18,489 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:13:18,489 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:13:18,489 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:13:18,489 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:13:18,489 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:13:18,489 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:13:18,500 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:13:18,512 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x126929c10>
+2025-05-30 00:13:18,512 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x114324f80> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:13:18,637 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1269559d0>
+2025-05-30 00:13:18,637 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x126ecbf50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:13:18,786 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12696e0d0>
+2025-05-30 00:13:18,787 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:13:18,789 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:13:18,792 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:13:18,792 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:13:18,793 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:13:18,873 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:13:18,912 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1251c2890>
+2025-05-30 00:13:18,912 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:13:18,913 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:13:18,913 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:13:18,913 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:13:18,913 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:13:18,927 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:13:18 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:13:18,927 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:13:18,927 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:13:18,927 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:13:18,928 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:13:18,928 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:13:18,928 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:13:18,928 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:13:19,052 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:13:19 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:13:19,052 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:13:19,052 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:13:19,053 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:13:19,053 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:13:19,053 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:13:19,053 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:13:19,053 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:13:19,638 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:13:19,859 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:14:24,341 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:14:24,341 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:14:24,341 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:14:24,341 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:14:24,341 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:14:24,341 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:14:24,341 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:14:24,341 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:14:24,341 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:14:24,341 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:14:24,345 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:14:24,345 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:14:24,811 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:14:24,811 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:14:24,811 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:14:24,811 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:14:24,811 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:14:24,811 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:14:24,812 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:14:24,812 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:14:24,812 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:14:24,812 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:14:24,812 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:14:24,814 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:14:24,827 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:14:24,833 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:14:24,917 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:14:24,952 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:14:24,952 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1251960d0>
+2025-05-30 00:14:24,953 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:14:24,953 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:14:24,953 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:14:24,953 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:14:24,953 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:14:24,953 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:14:24 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:14:24,954 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:14:24,954 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:14:24,954 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:14:24,954 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:14:24,954 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:14:24,954 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:14:24,954 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:14:24,954 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:14:24,955 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1252ce850>
+2025-05-30 00:14:24,955 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:14:24,955 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:14:24,955 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:14:24,955 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:14:24,955 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:14:24,961 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:14:24 GMT'), (b'server', b'uvicorn'), (b'content-length', b'106654'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:14:24,961 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:14:24,961 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:14:24,961 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:14:24,961 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:14:24,961 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:14:24,961 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:14:24,961 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:14:24,972 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:14:24,993 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x123b92350>
+2025-05-30 00:14:24,993 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x123891760> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:14:25,111 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x123b90790>
+2025-05-30 00:14:25,111 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x12522bf50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:14:25,273 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x123b28210>
+2025-05-30 00:14:25,273 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:14:25,273 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:14:25,274 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:14:25,274 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:14:25,274 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:14:25,389 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x125311390>
+2025-05-30 00:14:25,389 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:14:25,389 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:14:25,389 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:14:25,389 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:14:25,390 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:14:25,414 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:14:25 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:14:25,414 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:14:25,414 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:14:25,415 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:14:25,415 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:14:25,415 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:14:25,415 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:14:25,415 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:14:25,495 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:14:25,530 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:14:25 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:14:25,531 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:14:25,531 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:14:25,532 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:14:25,532 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:14:25,532 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:14:25,532 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:14:25,533 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:14:26,127 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:14:26,354 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:14:28,000 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:14:28,001 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:14:28,001 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:14:28,001 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:14:28,001 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:14:28,001 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:14:28,001 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:14:28,001 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:14:28,001 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:16:16,934 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:16:16,934 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:16:16,934 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:16:16,934 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:16:16,934 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:16:16,934 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:16:16,934 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:16:16,934 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:16:16,934 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:16:16,934 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:16:16,939 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:16:16,939 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:16:17,437 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:16:17,437 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:16:17,437 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:16:17,437 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:16:17,437 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:16:17,437 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:16:17,437 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:16:17,437 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:16:17,437 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:16:17,437 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:16:17,437 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:16:17,439 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:16:17,452 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:16:17,458 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:16:17,529 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:16:17,563 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:16:17,563 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11fe09310>
+2025-05-30 00:16:17,563 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:16:17,563 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:16:17,563 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:16:17,564 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:16:17,564 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:16:17,564 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:16:17 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:16:17,564 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:16:17,564 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:16:17,564 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:16:17,564 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:16:17,564 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:16:17,564 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:16:17,564 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:16:17,565 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:16:17,565 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11fe0a1d0>
+2025-05-30 00:16:17,565 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:16:17,565 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:16:17,565 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:16:17,565 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:16:17,565 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:16:17,571 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:16:17 GMT'), (b'server', b'uvicorn'), (b'content-length', b'106648'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:16:17,571 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:16:17,571 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:16:17,571 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:16:17,571 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:16:17,571 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:16:17,572 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:16:17,572 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:16:17,582 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:16:17,653 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11f4ce7d0>
+2025-05-30 00:16:17,654 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x10eb24f80> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:16:17,724 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x10b057510>
+2025-05-30 00:16:17,724 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x11fbcbf50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:16:17,729 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:16:17,936 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11ed5ca10>
+2025-05-30 00:16:17,936 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:16:17,937 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:16:17,937 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:16:17,937 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:16:17,937 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:16:18,009 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11ea12750>
+2025-05-30 00:16:18,009 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:16:18,011 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:16:18,011 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:16:18,011 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:16:18,011 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:16:18,080 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:16:18 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:16:18,080 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:16:18,080 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:16:18,081 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:16:18,081 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:16:18,081 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:16:18,081 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:16:18,082 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:16:18,155 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:16:18 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:16:18,156 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:16:18,156 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:16:18,157 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:16:18,157 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:16:18,157 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:16:18,157 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:16:18,157 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:16:18,761 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:16:18,778 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:16:18,778 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:16:18,778 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:16:18,779 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:16:18,779 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:16:18,779 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:16:18,779 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:16:18,779 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:16:18,779 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:16:18,982 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:16:30,473 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:16:30,473 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:16:30,473 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:16:30,473 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:16:30,474 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:16:30,474 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:16:30,474 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:16:30,474 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:16:30,474 - auto_diffusers - INFO - Starting code generation for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:16:30,474 - auto_diffusers - DEBUG - Parameters: prompt='A cat holding a sign that says hello world...', size=(768, 1360), steps=4
+2025-05-30 00:16:30,474 - auto_diffusers - DEBUG - Manual specs: True, Memory analysis provided: True
+2025-05-30 00:16:30,474 - auto_diffusers - INFO - Using manual hardware specifications
+2025-05-30 00:16:30,474 - auto_diffusers - DEBUG - Manual specs: {'platform': 'Linux', 'architecture': 'manual_input', 'cpu_count': 8, 'python_version': '3.11', 'cuda_available': False, 'mps_available': False, 'torch_version': '2.0+', 'manual_input': True, 'ram_gb': 16, 'user_dtype': None, 'gpu_info': None}
+2025-05-30 00:16:30,474 - auto_diffusers - INFO - No GPU detected, using CPU-only profile
+2025-05-30 00:16:30,475 - auto_diffusers - INFO - Selected optimization profile: cpu_only
+2025-05-30 00:16:30,475 - auto_diffusers - DEBUG - Creating generation prompt for Gemini API
+2025-05-30 00:16:30,475 - auto_diffusers - DEBUG - Prompt length: 7566 characters
+2025-05-30 00:16:30,475 - auto_diffusers - INFO - ================================================================================
+2025-05-30 00:16:30,475 - auto_diffusers - INFO - PROMPT SENT TO GEMINI API:
+2025-05-30 00:16:30,475 - auto_diffusers - INFO - ================================================================================
+2025-05-30 00:16:30,475 - auto_diffusers - INFO - 
+You are an expert in optimizing diffusers library code for different hardware configurations.
+
+NOTE: This system includes curated optimization knowledge from HuggingFace documentation.
+
+TASK: Generate optimized Python code for running a diffusion model with the following specifications:
+- Model: black-forest-labs/FLUX.1-schnell
+- Prompt: "A cat holding a sign that says hello world"
+- Image size: 768x1360
+- Inference steps: 4
+
+HARDWARE SPECIFICATIONS:
+- Platform: Linux (manual_input)
+- CPU Cores: 8
+- CUDA Available: False
+- MPS Available: False
+- Optimization Profile: cpu_only
+
+MEMORY ANALYSIS:
+- Model Memory Requirements: 36.0 GB (FP16 inference)
+- Model Weights Size: 24.0 GB (FP16)
+- Memory Recommendation: 🔄 Requires sequential CPU offloading
+- Recommended Precision: float16
+- Attention Slicing Recommended: True
+- VAE Slicing Recommended: True
+
+OPTIMIZATION KNOWLEDGE BASE:
+
+# DIFFUSERS OPTIMIZATION TECHNIQUES
+
+## Memory Optimization Techniques
+
+### 1. Model CPU Offloading
+Use `enable_model_cpu_offload()` to move models between GPU and CPU automatically:
+```python
+pipe.enable_model_cpu_offload()
+```
+- Saves significant VRAM by keeping only active models on GPU
+- Automatic management, no manual intervention needed
+- Compatible with all pipelines
+
+### 2. Sequential CPU Offloading  
+Use `enable_sequential_cpu_offload()` for more aggressive memory saving:
+```python
+pipe.enable_sequential_cpu_offload()
+```
+- More memory efficient than model offloading
+- Moves models to CPU after each forward pass
+- Best for very limited VRAM scenarios
+
+### 3. Attention Slicing
+Use `enable_attention_slicing()` to reduce memory during attention computation:
+```python
+pipe.enable_attention_slicing()
+# or specify slice size
+pipe.enable_attention_slicing("max")  # maximum slicing
+pipe.enable_attention_slicing(1)      # slice_size = 1
+```
+- Trades compute time for memory
+- Most effective for high-resolution images
+- Can be combined with other techniques
+
+### 4. VAE Slicing
+Use `enable_vae_slicing()` for large batch processing:
+```python
+pipe.enable_vae_slicing()
+```
+- Decodes images one at a time instead of all at once
+- Essential for batch sizes > 4
+- Minimal performance impact on single images
+
+### 5. VAE Tiling
+Use `enable_vae_tiling()` for high-resolution image generation:
+```python
+pipe.enable_vae_tiling()
+```
+- Enables 4K+ image generation on 8GB VRAM
+- Splits images into overlapping tiles
+- Automatically disabled for 512x512 or smaller images
+
+### 6. Memory Efficient Attention (xFormers)
+Use `enable_xformers_memory_efficient_attention()` if xFormers is installed:
+```python
+pipe.enable_xformers_memory_efficient_attention()
+```
+- Significantly reduces memory usage and improves speed
+- Requires xformers library installation
+- Compatible with most models
+
+## Performance Optimization Techniques
+
+### 1. Half Precision (FP16/BF16)
+Use lower precision for better memory and speed:
+```python
+# FP16 (widely supported)
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+
+# BF16 (better numerical stability, newer hardware)
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+```
+- FP16: Halves memory usage, widely supported
+- BF16: Better numerical stability, requires newer GPUs
+- Essential for most optimization scenarios
+
+### 2. Torch Compile (PyTorch 2.0+)
+Use `torch.compile()` for significant speed improvements:
+```python
+pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+# For some models, compile VAE too:
+pipe.vae.decode = torch.compile(pipe.vae.decode, mode="reduce-overhead", fullgraph=True)
+```
+- 5-50% speed improvement
+- Requires PyTorch 2.0+
+- First run is slower due to compilation
+
+### 3. Fast Schedulers
+Use faster schedulers for fewer steps:
+```python
+from diffusers import LMSDiscreteScheduler, UniPCMultistepScheduler
+
+# LMS Scheduler (good quality, fast)
+pipe.scheduler = LMSDiscreteScheduler.from_config(pipe.scheduler.config)
+
+# UniPC Scheduler (fastest)
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+```
+
+## Hardware-Specific Optimizations
+
+### NVIDIA GPU Optimizations
+```python
+# Enable Tensor Cores
+torch.backends.cudnn.benchmark = True
+
+# Optimal data type for NVIDIA
+torch_dtype = torch.float16  # or torch.bfloat16 for RTX 30/40 series
+```
+
+### Apple Silicon (MPS) Optimizations
+```python
+# Use MPS device
+device = "mps" if torch.backends.mps.is_available() else "cpu"
+pipe = pipe.to(device)
+
+# Recommended dtype for Apple Silicon
+torch_dtype = torch.bfloat16  # Better than float16 on Apple Silicon
+
+# Attention slicing often helps on MPS
+pipe.enable_attention_slicing()
+```
+
+### CPU Optimizations
+```python
+# Use float32 for CPU
+torch_dtype = torch.float32
+
+# Enable optimized attention
+pipe.enable_attention_slicing()
+```
+
+## Model-Specific Guidelines
+
+### FLUX Models
+- Do NOT use guidance_scale parameter (not needed for FLUX)
+- Use 4-8 inference steps maximum
+- BF16 dtype recommended
+- Enable attention slicing for memory optimization
+
+### Stable Diffusion XL
+- Enable attention slicing for high resolutions
+- Use refiner model sparingly to save memory
+- Consider VAE tiling for >1024px images
+
+### Stable Diffusion 1.5/2.1
+- Very memory efficient base models
+- Can often run without optimizations on 8GB+ VRAM
+- Enable VAE slicing for batch processing
+
+## Memory Usage Estimation
+- FLUX.1: ~24GB for full precision, ~12GB for FP16
+- SDXL: ~7GB for FP16, ~14GB for FP32
+- SD 1.5: ~2GB for FP16, ~4GB for FP32
+
+## Optimization Combinations by VRAM
+
+### 24GB+ VRAM (High-end)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+pipe = pipe.to("cuda")
+pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+```
+
+### 12-24GB VRAM (Mid-range)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+pipe.enable_model_cpu_offload()
+pipe.enable_xformers_memory_efficient_attention()
+```
+
+### 8-12GB VRAM (Entry-level)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe.enable_sequential_cpu_offload()
+pipe.enable_attention_slicing()
+pipe.enable_vae_slicing()
+pipe.enable_xformers_memory_efficient_attention()
+```
+
+### <8GB VRAM (Low-end)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe.enable_sequential_cpu_offload()
+pipe.enable_attention_slicing("max")
+pipe.enable_vae_slicing()
+pipe.enable_vae_tiling()
+```
+
+
+IMPORTANT: For FLUX.1-schnell models, do NOT include guidance_scale parameter as it's not needed.
+
+Using the OPTIMIZATION KNOWLEDGE BASE above, generate Python code that:
+
+1. **Selects the best optimization techniques** for the specific hardware profile
+2. **Applies appropriate memory optimizations** based on available VRAM
+3. **Uses optimal data types** for the target hardware:
+   - User specified dtype (if provided): Use exactly as specified
+   - Apple Silicon (MPS): prefer torch.bfloat16
+   - NVIDIA GPUs: prefer torch.float16 or torch.bfloat16 
+   - CPU only: use torch.float32
+4. **Implements hardware-specific optimizations** (CUDA, MPS, CPU)
+5. **Follows model-specific guidelines** (e.g., FLUX guidance_scale handling)
+
+IMPORTANT GUIDELINES:
+- Reference the OPTIMIZATION KNOWLEDGE BASE to select appropriate techniques
+- Include all necessary imports
+- Add brief comments explaining optimization choices
+- Generate compact, production-ready code
+- Inline values where possible for concise code
+- Generate ONLY the Python code, no explanations before or after the code block
+
+2025-05-30 00:16:30,475 - auto_diffusers - INFO - ================================================================================
+2025-05-30 00:16:30,475 - auto_diffusers - INFO - Sending request to Gemini API
+2025-05-30 00:16:45,777 - auto_diffusers - INFO - Successfully received response from Gemini API (no tools used)
+2025-05-30 00:16:45,777 - auto_diffusers - DEBUG - Response length: 2393 characters
+2025-05-30 00:20:26,203 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:20:26,203 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:20:26,203 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:20:26,203 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:20:26,203 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:20:26,203 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:20:26,203 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:20:26,204 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:20:26,204 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:20:26,204 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:20:26,207 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:20:26,208 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:20:26,674 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:20:26,674 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:20:26,674 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:20:26,674 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:20:26,674 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:20:26,674 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:20:26,674 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:20:26,674 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:20:26,674 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:20:26,674 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:20:26,674 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:20:26,676 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:20:26,689 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:20:26,695 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:20:26,775 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:20:26,809 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:20:26,809 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x113d738d0>
+2025-05-30 00:20:26,810 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:20:26,810 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:20:26,810 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:20:26,810 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:20:26,810 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:20:26,810 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:20:26 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:20:26,810 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:20:26,811 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:20:26,811 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:20:26,811 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:20:26,811 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:20:26,811 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:20:26,811 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:20:26,811 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:20:26,812 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x133f15cd0>
+2025-05-30 00:20:26,812 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:20:26,812 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:20:26,812 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:20:26,812 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:20:26,812 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:20:26,818 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:20:26 GMT'), (b'server', b'uvicorn'), (b'content-length', b'104665'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:20:26,818 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:20:26,818 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:20:26,818 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:20:26,819 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:20:26,819 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:20:26,819 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:20:26,819 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:20:26,829 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:20:26,983 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:20:27,005 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1274efd50>
+2025-05-30 00:20:27,005 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12705e9d0>
+2025-05-30 00:20:27,005 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x127b8d760> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:20:27,005 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x1312cbf50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:20:27,291 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x131118190>
+2025-05-30 00:20:27,291 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x127ec0ad0>
+2025-05-30 00:20:27,291 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:20:27,292 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:20:27,292 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:20:27,292 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:20:27,292 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:20:27,292 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:20:27,292 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:20:27,293 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:20:27,293 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:20:27,293 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:20:27,437 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:20:27 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:20:27,437 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:20:27,437 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:20:27,438 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:20:27,438 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:20:27,438 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:20:27,438 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:20:27,439 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:20:27 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:20:27,439 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:20:27,439 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:20:27,439 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:20:27,440 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:20:27,440 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:20:27,440 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:20:27,440 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:20:27,440 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:20:28,103 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:20:28,371 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:20:28,686 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:20:28,686 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:20:28,686 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:20:28,686 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:20:28,686 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:20:28,687 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:20:28,687 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:20:28,687 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:20:28,687 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:20:30,112 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:20:30,112 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:20:30,112 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:20:30,112 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:20:30,112 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:20:30,112 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:20:30,112 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:20:30,112 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:20:30,112 - auto_diffusers - INFO - Starting code generation for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:20:30,112 - auto_diffusers - DEBUG - Parameters: prompt='A cat holding a sign that says hello world...', size=(768, 1360), steps=4
+2025-05-30 00:20:30,112 - auto_diffusers - DEBUG - Manual specs: True, Memory analysis provided: True
+2025-05-30 00:20:30,112 - auto_diffusers - INFO - Using manual hardware specifications
+2025-05-30 00:20:30,112 - auto_diffusers - DEBUG - Manual specs: {'platform': 'Linux', 'architecture': 'manual_input', 'cpu_count': 8, 'python_version': '3.11', 'cuda_available': False, 'mps_available': False, 'torch_version': '2.0+', 'manual_input': True, 'ram_gb': 16, 'user_dtype': None, 'gpu_info': None}
+2025-05-30 00:20:30,112 - auto_diffusers - INFO - No GPU detected, using CPU-only profile
+2025-05-30 00:20:30,112 - auto_diffusers - INFO - Selected optimization profile: cpu_only
+2025-05-30 00:20:30,112 - auto_diffusers - DEBUG - Creating generation prompt for Gemini API
+2025-05-30 00:20:30,112 - auto_diffusers - DEBUG - Prompt length: 7566 characters
+2025-05-30 00:20:30,112 - auto_diffusers - INFO - ================================================================================
+2025-05-30 00:20:30,112 - auto_diffusers - INFO - PROMPT SENT TO GEMINI API:
+2025-05-30 00:20:30,112 - auto_diffusers - INFO - ================================================================================
+2025-05-30 00:20:30,112 - auto_diffusers - INFO - 
+You are an expert in optimizing diffusers library code for different hardware configurations.
+
+NOTE: This system includes curated optimization knowledge from HuggingFace documentation.
+
+TASK: Generate optimized Python code for running a diffusion model with the following specifications:
+- Model: black-forest-labs/FLUX.1-schnell
+- Prompt: "A cat holding a sign that says hello world"
+- Image size: 768x1360
+- Inference steps: 4
+
+HARDWARE SPECIFICATIONS:
+- Platform: Linux (manual_input)
+- CPU Cores: 8
+- CUDA Available: False
+- MPS Available: False
+- Optimization Profile: cpu_only
+
+MEMORY ANALYSIS:
+- Model Memory Requirements: 36.0 GB (FP16 inference)
+- Model Weights Size: 24.0 GB (FP16)
+- Memory Recommendation: 🔄 Requires sequential CPU offloading
+- Recommended Precision: float16
+- Attention Slicing Recommended: True
+- VAE Slicing Recommended: True
+
+OPTIMIZATION KNOWLEDGE BASE:
+
+# DIFFUSERS OPTIMIZATION TECHNIQUES
+
+## Memory Optimization Techniques
+
+### 1. Model CPU Offloading
+Use `enable_model_cpu_offload()` to move models between GPU and CPU automatically:
+```python
+pipe.enable_model_cpu_offload()
+```
+- Saves significant VRAM by keeping only active models on GPU
+- Automatic management, no manual intervention needed
+- Compatible with all pipelines
+
+### 2. Sequential CPU Offloading  
+Use `enable_sequential_cpu_offload()` for more aggressive memory saving:
+```python
+pipe.enable_sequential_cpu_offload()
+```
+- More memory efficient than model offloading
+- Moves models to CPU after each forward pass
+- Best for very limited VRAM scenarios
+
+### 3. Attention Slicing
+Use `enable_attention_slicing()` to reduce memory during attention computation:
+```python
+pipe.enable_attention_slicing()
+# or specify slice size
+pipe.enable_attention_slicing("max")  # maximum slicing
+pipe.enable_attention_slicing(1)      # slice_size = 1
+```
+- Trades compute time for memory
+- Most effective for high-resolution images
+- Can be combined with other techniques
+
+### 4. VAE Slicing
+Use `enable_vae_slicing()` for large batch processing:
+```python
+pipe.enable_vae_slicing()
+```
+- Decodes images one at a time instead of all at once
+- Essential for batch sizes > 4
+- Minimal performance impact on single images
+
+### 5. VAE Tiling
+Use `enable_vae_tiling()` for high-resolution image generation:
+```python
+pipe.enable_vae_tiling()
+```
+- Enables 4K+ image generation on 8GB VRAM
+- Splits images into overlapping tiles
+- Automatically disabled for 512x512 or smaller images
+
+### 6. Memory Efficient Attention (xFormers)
+Use `enable_xformers_memory_efficient_attention()` if xFormers is installed:
+```python
+pipe.enable_xformers_memory_efficient_attention()
+```
+- Significantly reduces memory usage and improves speed
+- Requires xformers library installation
+- Compatible with most models
+
+## Performance Optimization Techniques
+
+### 1. Half Precision (FP16/BF16)
+Use lower precision for better memory and speed:
+```python
+# FP16 (widely supported)
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+
+# BF16 (better numerical stability, newer hardware)
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+```
+- FP16: Halves memory usage, widely supported
+- BF16: Better numerical stability, requires newer GPUs
+- Essential for most optimization scenarios
+
+### 2. Torch Compile (PyTorch 2.0+)
+Use `torch.compile()` for significant speed improvements:
+```python
+pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+# For some models, compile VAE too:
+pipe.vae.decode = torch.compile(pipe.vae.decode, mode="reduce-overhead", fullgraph=True)
+```
+- 5-50% speed improvement
+- Requires PyTorch 2.0+
+- First run is slower due to compilation
+
+### 3. Fast Schedulers
+Use faster schedulers for fewer steps:
+```python
+from diffusers import LMSDiscreteScheduler, UniPCMultistepScheduler
+
+# LMS Scheduler (good quality, fast)
+pipe.scheduler = LMSDiscreteScheduler.from_config(pipe.scheduler.config)
+
+# UniPC Scheduler (fastest)
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+```
+
+## Hardware-Specific Optimizations
+
+### NVIDIA GPU Optimizations
+```python
+# Enable Tensor Cores
+torch.backends.cudnn.benchmark = True
+
+# Optimal data type for NVIDIA
+torch_dtype = torch.float16  # or torch.bfloat16 for RTX 30/40 series
+```
+
+### Apple Silicon (MPS) Optimizations
+```python
+# Use MPS device
+device = "mps" if torch.backends.mps.is_available() else "cpu"
+pipe = pipe.to(device)
+
+# Recommended dtype for Apple Silicon
+torch_dtype = torch.bfloat16  # Better than float16 on Apple Silicon
+
+# Attention slicing often helps on MPS
+pipe.enable_attention_slicing()
+```
+
+### CPU Optimizations
+```python
+# Use float32 for CPU
+torch_dtype = torch.float32
+
+# Enable optimized attention
+pipe.enable_attention_slicing()
+```
+
+## Model-Specific Guidelines
+
+### FLUX Models
+- Do NOT use guidance_scale parameter (not needed for FLUX)
+- Use 4-8 inference steps maximum
+- BF16 dtype recommended
+- Enable attention slicing for memory optimization
+
+### Stable Diffusion XL
+- Enable attention slicing for high resolutions
+- Use refiner model sparingly to save memory
+- Consider VAE tiling for >1024px images
+
+### Stable Diffusion 1.5/2.1
+- Very memory efficient base models
+- Can often run without optimizations on 8GB+ VRAM
+- Enable VAE slicing for batch processing
+
+## Memory Usage Estimation
+- FLUX.1: ~24GB for full precision, ~12GB for FP16
+- SDXL: ~7GB for FP16, ~14GB for FP32
+- SD 1.5: ~2GB for FP16, ~4GB for FP32
+
+## Optimization Combinations by VRAM
+
+### 24GB+ VRAM (High-end)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+pipe = pipe.to("cuda")
+pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+```
+
+### 12-24GB VRAM (Mid-range)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+pipe.enable_model_cpu_offload()
+pipe.enable_xformers_memory_efficient_attention()
+```
+
+### 8-12GB VRAM (Entry-level)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe.enable_sequential_cpu_offload()
+pipe.enable_attention_slicing()
+pipe.enable_vae_slicing()
+pipe.enable_xformers_memory_efficient_attention()
+```
+
+### <8GB VRAM (Low-end)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe.enable_sequential_cpu_offload()
+pipe.enable_attention_slicing("max")
+pipe.enable_vae_slicing()
+pipe.enable_vae_tiling()
+```
+
+
+IMPORTANT: For FLUX.1-schnell models, do NOT include guidance_scale parameter as it's not needed.
+
+Using the OPTIMIZATION KNOWLEDGE BASE above, generate Python code that:
+
+1. **Selects the best optimization techniques** for the specific hardware profile
+2. **Applies appropriate memory optimizations** based on available VRAM
+3. **Uses optimal data types** for the target hardware:
+   - User specified dtype (if provided): Use exactly as specified
+   - Apple Silicon (MPS): prefer torch.bfloat16
+   - NVIDIA GPUs: prefer torch.float16 or torch.bfloat16 
+   - CPU only: use torch.float32
+4. **Implements hardware-specific optimizations** (CUDA, MPS, CPU)
+5. **Follows model-specific guidelines** (e.g., FLUX guidance_scale handling)
+
+IMPORTANT GUIDELINES:
+- Reference the OPTIMIZATION KNOWLEDGE BASE to select appropriate techniques
+- Include all necessary imports
+- Add brief comments explaining optimization choices
+- Generate compact, production-ready code
+- Inline values where possible for concise code
+- Generate ONLY the Python code, no explanations before or after the code block
+
+2025-05-30 00:20:30,113 - auto_diffusers - INFO - ================================================================================
+2025-05-30 00:20:30,113 - auto_diffusers - INFO - Sending request to Gemini API
+2025-05-30 00:20:43,867 - auto_diffusers - INFO - Successfully received response from Gemini API (no tools used)
+2025-05-30 00:20:43,868 - auto_diffusers - DEBUG - Response length: 1716 characters
+2025-05-30 00:23:06,277 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:23:06,277 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:23:06,277 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:23:06,277 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:23:06,277 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:23:06,277 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:23:06,277 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:23:06,277 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:23:06,277 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:23:06,277 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:23:06,281 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:23:06,281 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:23:06,749 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:23:06,749 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:23:06,749 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:23:06,749 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:23:06,749 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:23:06,749 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:23:06,750 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:23:06,750 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:23:06,750 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:23:06,750 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:23:06,750 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:23:06,752 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:23:06,764 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:23:06,770 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:23:06,840 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:23:06,876 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:23:06,877 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12f96a010>
+2025-05-30 00:23:06,877 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:23:06,877 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:23:06,877 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:23:06,877 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:23:06,877 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:23:06,878 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:23:06 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:23:06,878 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:23:06,878 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:23:06,878 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:23:06,878 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:23:06,878 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:23:06,878 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:23:06,878 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:23:06,879 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:23:06,879 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12f96b050>
+2025-05-30 00:23:06,879 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:23:06,879 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:23:06,879 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:23:06,879 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:23:06,879 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:23:06,885 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:23:06 GMT'), (b'server', b'uvicorn'), (b'content-length', b'105144'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:23:06,885 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:23:06,885 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:23:06,885 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:23:06,885 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:23:06,885 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:23:06,885 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:23:06,885 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:23:06,896 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:23:06,961 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12ae9bd90>
+2025-05-30 00:23:06,961 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x12aa8d760> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:23:07,038 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12bc40450>
+2025-05-30 00:23:07,038 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x12bccbf50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:23:07,047 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:23:07,239 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12aeb6290>
+2025-05-30 00:23:07,240 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:23:07,240 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:23:07,240 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:23:07,240 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:23:07,240 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:23:07,323 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12a1fc550>
+2025-05-30 00:23:07,324 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:23:07,324 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:23:07,324 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:23:07,324 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:23:07,325 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:23:07,379 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:23:07 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:23:07,380 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:23:07,380 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:23:07,380 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:23:07,381 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:23:07,381 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:23:07,381 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:23:07,381 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:23:07,469 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:23:07 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:23:07,471 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:23:07,471 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:23:07,476 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:23:07,477 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:23:07,477 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:23:07,477 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:23:07,478 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:23:08,047 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:23:08,048 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:23:08,048 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:23:08,048 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:23:08,048 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:23:08,048 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:23:08,048 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:23:08,048 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:23:08,049 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:23:08,068 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:23:08,293 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:23:09,169 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:23:09,169 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:23:09,169 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:23:09,169 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:23:09,169 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:23:09,169 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:23:09,169 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:23:09,169 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:23:09,169 - auto_diffusers - INFO - Starting code generation for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:23:09,169 - auto_diffusers - DEBUG - Parameters: prompt='A cat holding a sign that says hello world...', size=(768, 1360), steps=4
+2025-05-30 00:23:09,169 - auto_diffusers - DEBUG - Manual specs: True, Memory analysis provided: True
+2025-05-30 00:23:09,169 - auto_diffusers - INFO - Using manual hardware specifications
+2025-05-30 00:23:09,169 - auto_diffusers - DEBUG - Manual specs: {'platform': 'Linux', 'architecture': 'manual_input', 'cpu_count': 8, 'python_version': '3.11', 'cuda_available': False, 'mps_available': False, 'torch_version': '2.0+', 'manual_input': True, 'ram_gb': 16, 'user_dtype': None, 'gpu_info': None}
+2025-05-30 00:23:09,169 - auto_diffusers - INFO - No GPU detected, using CPU-only profile
+2025-05-30 00:23:09,169 - auto_diffusers - INFO - Selected optimization profile: cpu_only
+2025-05-30 00:23:09,169 - auto_diffusers - DEBUG - Creating generation prompt for Gemini API
+2025-05-30 00:23:09,169 - auto_diffusers - DEBUG - Prompt length: 7566 characters
+2025-05-30 00:23:09,169 - auto_diffusers - INFO - ================================================================================
+2025-05-30 00:23:09,169 - auto_diffusers - INFO - PROMPT SENT TO GEMINI API:
+2025-05-30 00:23:09,169 - auto_diffusers - INFO - ================================================================================
+2025-05-30 00:23:09,169 - auto_diffusers - INFO - 
+You are an expert in optimizing diffusers library code for different hardware configurations.
+
+NOTE: This system includes curated optimization knowledge from HuggingFace documentation.
+
+TASK: Generate optimized Python code for running a diffusion model with the following specifications:
+- Model: black-forest-labs/FLUX.1-schnell
+- Prompt: "A cat holding a sign that says hello world"
+- Image size: 768x1360
+- Inference steps: 4
+
+HARDWARE SPECIFICATIONS:
+- Platform: Linux (manual_input)
+- CPU Cores: 8
+- CUDA Available: False
+- MPS Available: False
+- Optimization Profile: cpu_only
+
+MEMORY ANALYSIS:
+- Model Memory Requirements: 36.0 GB (FP16 inference)
+- Model Weights Size: 24.0 GB (FP16)
+- Memory Recommendation: 🔄 Requires sequential CPU offloading
+- Recommended Precision: float16
+- Attention Slicing Recommended: True
+- VAE Slicing Recommended: True
+
+OPTIMIZATION KNOWLEDGE BASE:
+
+# DIFFUSERS OPTIMIZATION TECHNIQUES
+
+## Memory Optimization Techniques
+
+### 1. Model CPU Offloading
+Use `enable_model_cpu_offload()` to move models between GPU and CPU automatically:
+```python
+pipe.enable_model_cpu_offload()
+```
+- Saves significant VRAM by keeping only active models on GPU
+- Automatic management, no manual intervention needed
+- Compatible with all pipelines
+
+### 2. Sequential CPU Offloading  
+Use `enable_sequential_cpu_offload()` for more aggressive memory saving:
+```python
+pipe.enable_sequential_cpu_offload()
+```
+- More memory efficient than model offloading
+- Moves models to CPU after each forward pass
+- Best for very limited VRAM scenarios
+
+### 3. Attention Slicing
+Use `enable_attention_slicing()` to reduce memory during attention computation:
+```python
+pipe.enable_attention_slicing()
+# or specify slice size
+pipe.enable_attention_slicing("max")  # maximum slicing
+pipe.enable_attention_slicing(1)      # slice_size = 1
+```
+- Trades compute time for memory
+- Most effective for high-resolution images
+- Can be combined with other techniques
+
+### 4. VAE Slicing
+Use `enable_vae_slicing()` for large batch processing:
+```python
+pipe.enable_vae_slicing()
+```
+- Decodes images one at a time instead of all at once
+- Essential for batch sizes > 4
+- Minimal performance impact on single images
+
+### 5. VAE Tiling
+Use `enable_vae_tiling()` for high-resolution image generation:
+```python
+pipe.enable_vae_tiling()
+```
+- Enables 4K+ image generation on 8GB VRAM
+- Splits images into overlapping tiles
+- Automatically disabled for 512x512 or smaller images
+
+### 6. Memory Efficient Attention (xFormers)
+Use `enable_xformers_memory_efficient_attention()` if xFormers is installed:
+```python
+pipe.enable_xformers_memory_efficient_attention()
+```
+- Significantly reduces memory usage and improves speed
+- Requires xformers library installation
+- Compatible with most models
+
+## Performance Optimization Techniques
+
+### 1. Half Precision (FP16/BF16)
+Use lower precision for better memory and speed:
+```python
+# FP16 (widely supported)
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+
+# BF16 (better numerical stability, newer hardware)
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+```
+- FP16: Halves memory usage, widely supported
+- BF16: Better numerical stability, requires newer GPUs
+- Essential for most optimization scenarios
+
+### 2. Torch Compile (PyTorch 2.0+)
+Use `torch.compile()` for significant speed improvements:
+```python
+pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+# For some models, compile VAE too:
+pipe.vae.decode = torch.compile(pipe.vae.decode, mode="reduce-overhead", fullgraph=True)
+```
+- 5-50% speed improvement
+- Requires PyTorch 2.0+
+- First run is slower due to compilation
+
+### 3. Fast Schedulers
+Use faster schedulers for fewer steps:
+```python
+from diffusers import LMSDiscreteScheduler, UniPCMultistepScheduler
+
+# LMS Scheduler (good quality, fast)
+pipe.scheduler = LMSDiscreteScheduler.from_config(pipe.scheduler.config)
+
+# UniPC Scheduler (fastest)
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+```
+
+## Hardware-Specific Optimizations
+
+### NVIDIA GPU Optimizations
+```python
+# Enable Tensor Cores
+torch.backends.cudnn.benchmark = True
+
+# Optimal data type for NVIDIA
+torch_dtype = torch.float16  # or torch.bfloat16 for RTX 30/40 series
+```
+
+### Apple Silicon (MPS) Optimizations
+```python
+# Use MPS device
+device = "mps" if torch.backends.mps.is_available() else "cpu"
+pipe = pipe.to(device)
+
+# Recommended dtype for Apple Silicon
+torch_dtype = torch.bfloat16  # Better than float16 on Apple Silicon
+
+# Attention slicing often helps on MPS
+pipe.enable_attention_slicing()
+```
+
+### CPU Optimizations
+```python
+# Use float32 for CPU
+torch_dtype = torch.float32
+
+# Enable optimized attention
+pipe.enable_attention_slicing()
+```
+
+## Model-Specific Guidelines
+
+### FLUX Models
+- Do NOT use guidance_scale parameter (not needed for FLUX)
+- Use 4-8 inference steps maximum
+- BF16 dtype recommended
+- Enable attention slicing for memory optimization
+
+### Stable Diffusion XL
+- Enable attention slicing for high resolutions
+- Use refiner model sparingly to save memory
+- Consider VAE tiling for >1024px images
+
+### Stable Diffusion 1.5/2.1
+- Very memory efficient base models
+- Can often run without optimizations on 8GB+ VRAM
+- Enable VAE slicing for batch processing
+
+## Memory Usage Estimation
+- FLUX.1: ~24GB for full precision, ~12GB for FP16
+- SDXL: ~7GB for FP16, ~14GB for FP32
+- SD 1.5: ~2GB for FP16, ~4GB for FP32
+
+## Optimization Combinations by VRAM
+
+### 24GB+ VRAM (High-end)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+pipe = pipe.to("cuda")
+pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+```
+
+### 12-24GB VRAM (Mid-range)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+pipe.enable_model_cpu_offload()
+pipe.enable_xformers_memory_efficient_attention()
+```
+
+### 8-12GB VRAM (Entry-level)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe.enable_sequential_cpu_offload()
+pipe.enable_attention_slicing()
+pipe.enable_vae_slicing()
+pipe.enable_xformers_memory_efficient_attention()
+```
+
+### <8GB VRAM (Low-end)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe.enable_sequential_cpu_offload()
+pipe.enable_attention_slicing("max")
+pipe.enable_vae_slicing()
+pipe.enable_vae_tiling()
+```
+
+
+IMPORTANT: For FLUX.1-schnell models, do NOT include guidance_scale parameter as it's not needed.
+
+Using the OPTIMIZATION KNOWLEDGE BASE above, generate Python code that:
+
+1. **Selects the best optimization techniques** for the specific hardware profile
+2. **Applies appropriate memory optimizations** based on available VRAM
+3. **Uses optimal data types** for the target hardware:
+   - User specified dtype (if provided): Use exactly as specified
+   - Apple Silicon (MPS): prefer torch.bfloat16
+   - NVIDIA GPUs: prefer torch.float16 or torch.bfloat16 
+   - CPU only: use torch.float32
+4. **Implements hardware-specific optimizations** (CUDA, MPS, CPU)
+5. **Follows model-specific guidelines** (e.g., FLUX guidance_scale handling)
+
+IMPORTANT GUIDELINES:
+- Reference the OPTIMIZATION KNOWLEDGE BASE to select appropriate techniques
+- Include all necessary imports
+- Add brief comments explaining optimization choices
+- Generate compact, production-ready code
+- Inline values where possible for concise code
+- Generate ONLY the Python code, no explanations before or after the code block
+
+2025-05-30 00:23:09,170 - auto_diffusers - INFO - ================================================================================
+2025-05-30 00:23:09,170 - auto_diffusers - INFO - Sending request to Gemini API
+2025-05-30 00:23:21,834 - auto_diffusers - INFO - Successfully received response from Gemini API (no tools used)
+2025-05-30 00:23:21,836 - auto_diffusers - DEBUG - Response length: 1661 characters
+2025-05-30 00:27:11,690 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:27:11,690 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:27:11,690 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:27:11,690 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:27:11,690 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:27:11,690 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:27:11,690 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:27:11,690 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:27:11,690 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:27:11,690 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:27:11,695 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:27:11,695 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:27:12,187 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:27:12,187 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:27:12,187 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:27:12,187 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:27:12,187 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:27:12,187 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:27:12,187 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:27:12,187 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:27:12,187 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:27:12,188 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:27:12,188 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:27:12,190 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:27:12,203 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:27:12,207 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:27:12,282 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:27:12,315 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:27:12,315 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1297b9e10>
+2025-05-30 00:27:12,315 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:27:12,316 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:27:12,316 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:27:12,316 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:27:12,316 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:27:12,316 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:27:12 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:27:12,316 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:27:12,316 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:27:12,316 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:27:12,316 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:27:12,316 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:27:12,316 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:27:12,317 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:27:12,317 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:27:12,317 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x129a6e510>
+2025-05-30 00:27:12,317 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:27:12,318 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:27:12,318 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:27:12,318 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:27:12,318 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:27:12,324 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:27:12 GMT'), (b'server', b'uvicorn'), (b'content-length', b'105338'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:27:12,324 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:27:12,324 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:27:12,324 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:27:12,324 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:27:12,325 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:27:12,325 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:27:12,325 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:27:12,335 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:27:12,366 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x128a7f450>
+2025-05-30 00:27:12,366 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x119e28f80> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:27:12,478 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x128ae9310>
+2025-05-30 00:27:12,478 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x1298cbf50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:27:12,484 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:27:12,648 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x128a75c10>
+2025-05-30 00:27:12,649 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:27:12,649 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:27:12,649 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:27:12,649 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:27:12,649 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:27:12,762 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x128a4f710>
+2025-05-30 00:27:12,762 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:27:12,762 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:27:12,762 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:27:12,762 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:27:12,762 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:27:12,793 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:27:12 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:27:12,793 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:27:12,793 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:27:12,793 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:27:12,793 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:27:12,793 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:27:12,793 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:27:12,793 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:27:12,907 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:27:12 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:27:12,907 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:27:12,908 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:27:12,908 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:27:12,908 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:27:12,909 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:27:12,909 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:27:12,909 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:27:13,500 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:27:13,583 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:27:13,583 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:27:13,583 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:27:13,584 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:27:13,584 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:27:13,584 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:27:13,584 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:27:13,584 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:27:13,584 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:27:13,720 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:30:00,106 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:30:00,106 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:30:00,106 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:30:00,106 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:30:00,106 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:30:00,106 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:30:00,106 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:30:00,106 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:30:00,106 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:30:00,106 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:30:00,110 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:30:00,111 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:30:00,561 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:30:00,561 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:30:00,561 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:30:00,561 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:30:00,561 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:30:00,561 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:30:00,561 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:30:00,561 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:30:00,561 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:30:00,561 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:30:00,561 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:30:00,563 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:30:00,576 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:30:00,582 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:30:00,660 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:30:00,699 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:30:00,699 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x130969290>
+2025-05-30 00:30:00,699 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:30:00,699 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:30:00,700 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:30:00,700 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:30:00,700 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:30:00,700 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:30:00 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:30:00,701 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:30:00,701 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:30:00,701 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:30:00,701 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:30:00,701 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:30:00,701 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:30:00,701 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:30:00,701 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:30:00,703 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x130969d50>
+2025-05-30 00:30:00,704 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:30:00,704 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:30:00,704 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:30:00,704 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:30:00,704 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:30:00,713 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:30:00 GMT'), (b'server', b'uvicorn'), (b'content-length', b'105821'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:30:00,713 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:30:00,713 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:30:00,713 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:30:00,713 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:30:00,713 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:30:00,713 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:30:00,713 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:30:00,723 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:30:00,737 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x126a98ad0>
+2025-05-30 00:30:00,737 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x115b24f80> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:30:00,857 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:30:00,882 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x125420450>
+2025-05-30 00:30:00,882 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x127dabf50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:30:01,011 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x127d1fd50>
+2025-05-30 00:30:01,012 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:30:01,012 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:30:01,012 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:30:01,013 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:30:01,013 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:30:01,152 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:30:01 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:30:01,152 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:30:01,152 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:30:01,152 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:30:01,152 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:30:01,152 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:30:01,152 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:30:01,152 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:30:01,200 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1265be290>
+2025-05-30 00:30:01,200 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:30:01,200 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:30:01,200 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:30:01,200 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:30:01,200 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:30:01,362 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:30:01 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:30:01,362 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:30:01,362 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:30:01,363 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:30:01,363 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:30:01,363 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:30:01,363 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:30:01,363 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:30:01,967 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:30:01,967 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:30:01,968 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:30:01,968 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:30:01,968 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:30:01,968 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:30:01,968 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:30:01,968 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:30:01,968 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:30:01,968 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:30:02,190 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:30:05,722 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:30:05,722 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:30:05,723 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:30:05,723 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:30:05,723 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:30:05,723 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:30:05,723 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:30:05,723 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:30:05,723 - auto_diffusers - INFO - Starting code generation for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:30:05,724 - auto_diffusers - DEBUG - Parameters: prompt='A cat holding a sign that says hello world...', size=(768, 1360), steps=4
+2025-05-30 00:30:05,724 - auto_diffusers - DEBUG - Manual specs: True, Memory analysis provided: True
+2025-05-30 00:30:05,724 - auto_diffusers - INFO - Using manual hardware specifications
+2025-05-30 00:30:05,724 - auto_diffusers - DEBUG - Manual specs: {'platform': 'Linux', 'architecture': 'manual_input', 'cpu_count': 8, 'python_version': '3.11', 'cuda_available': False, 'mps_available': False, 'torch_version': '2.0+', 'manual_input': True, 'ram_gb': 16, 'user_dtype': None, 'gpu_info': None}
+2025-05-30 00:30:05,724 - auto_diffusers - INFO - No GPU detected, using CPU-only profile
+2025-05-30 00:30:05,724 - auto_diffusers - INFO - Selected optimization profile: cpu_only
+2025-05-30 00:30:05,724 - auto_diffusers - DEBUG - Creating generation prompt for Gemini API
+2025-05-30 00:30:05,725 - auto_diffusers - DEBUG - Prompt length: 7566 characters
+2025-05-30 00:30:05,725 - auto_diffusers - INFO - ================================================================================
+2025-05-30 00:30:05,725 - auto_diffusers - INFO - PROMPT SENT TO GEMINI API:
+2025-05-30 00:30:05,725 - auto_diffusers - INFO - ================================================================================
+2025-05-30 00:30:05,725 - auto_diffusers - INFO - 
+You are an expert in optimizing diffusers library code for different hardware configurations.
+
+NOTE: This system includes curated optimization knowledge from HuggingFace documentation.
+
+TASK: Generate optimized Python code for running a diffusion model with the following specifications:
+- Model: black-forest-labs/FLUX.1-schnell
+- Prompt: "A cat holding a sign that says hello world"
+- Image size: 768x1360
+- Inference steps: 4
+
+HARDWARE SPECIFICATIONS:
+- Platform: Linux (manual_input)
+- CPU Cores: 8
+- CUDA Available: False
+- MPS Available: False
+- Optimization Profile: cpu_only
+
+MEMORY ANALYSIS:
+- Model Memory Requirements: 36.0 GB (FP16 inference)
+- Model Weights Size: 24.0 GB (FP16)
+- Memory Recommendation: 🔄 Requires sequential CPU offloading
+- Recommended Precision: float16
+- Attention Slicing Recommended: True
+- VAE Slicing Recommended: True
+
+OPTIMIZATION KNOWLEDGE BASE:
+
+# DIFFUSERS OPTIMIZATION TECHNIQUES
+
+## Memory Optimization Techniques
+
+### 1. Model CPU Offloading
+Use `enable_model_cpu_offload()` to move models between GPU and CPU automatically:
+```python
+pipe.enable_model_cpu_offload()
+```
+- Saves significant VRAM by keeping only active models on GPU
+- Automatic management, no manual intervention needed
+- Compatible with all pipelines
+
+### 2. Sequential CPU Offloading  
+Use `enable_sequential_cpu_offload()` for more aggressive memory saving:
+```python
+pipe.enable_sequential_cpu_offload()
+```
+- More memory efficient than model offloading
+- Moves models to CPU after each forward pass
+- Best for very limited VRAM scenarios
+
+### 3. Attention Slicing
+Use `enable_attention_slicing()` to reduce memory during attention computation:
+```python
+pipe.enable_attention_slicing()
+# or specify slice size
+pipe.enable_attention_slicing("max")  # maximum slicing
+pipe.enable_attention_slicing(1)      # slice_size = 1
+```
+- Trades compute time for memory
+- Most effective for high-resolution images
+- Can be combined with other techniques
+
+### 4. VAE Slicing
+Use `enable_vae_slicing()` for large batch processing:
+```python
+pipe.enable_vae_slicing()
+```
+- Decodes images one at a time instead of all at once
+- Essential for batch sizes > 4
+- Minimal performance impact on single images
+
+### 5. VAE Tiling
+Use `enable_vae_tiling()` for high-resolution image generation:
+```python
+pipe.enable_vae_tiling()
+```
+- Enables 4K+ image generation on 8GB VRAM
+- Splits images into overlapping tiles
+- Automatically disabled for 512x512 or smaller images
+
+### 6. Memory Efficient Attention (xFormers)
+Use `enable_xformers_memory_efficient_attention()` if xFormers is installed:
+```python
+pipe.enable_xformers_memory_efficient_attention()
+```
+- Significantly reduces memory usage and improves speed
+- Requires xformers library installation
+- Compatible with most models
+
+## Performance Optimization Techniques
+
+### 1. Half Precision (FP16/BF16)
+Use lower precision for better memory and speed:
+```python
+# FP16 (widely supported)
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+
+# BF16 (better numerical stability, newer hardware)
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+```
+- FP16: Halves memory usage, widely supported
+- BF16: Better numerical stability, requires newer GPUs
+- Essential for most optimization scenarios
+
+### 2. Torch Compile (PyTorch 2.0+)
+Use `torch.compile()` for significant speed improvements:
+```python
+pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+# For some models, compile VAE too:
+pipe.vae.decode = torch.compile(pipe.vae.decode, mode="reduce-overhead", fullgraph=True)
+```
+- 5-50% speed improvement
+- Requires PyTorch 2.0+
+- First run is slower due to compilation
+
+### 3. Fast Schedulers
+Use faster schedulers for fewer steps:
+```python
+from diffusers import LMSDiscreteScheduler, UniPCMultistepScheduler
+
+# LMS Scheduler (good quality, fast)
+pipe.scheduler = LMSDiscreteScheduler.from_config(pipe.scheduler.config)
+
+# UniPC Scheduler (fastest)
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+```
+
+## Hardware-Specific Optimizations
+
+### NVIDIA GPU Optimizations
+```python
+# Enable Tensor Cores
+torch.backends.cudnn.benchmark = True
+
+# Optimal data type for NVIDIA
+torch_dtype = torch.float16  # or torch.bfloat16 for RTX 30/40 series
+```
+
+### Apple Silicon (MPS) Optimizations
+```python
+# Use MPS device
+device = "mps" if torch.backends.mps.is_available() else "cpu"
+pipe = pipe.to(device)
+
+# Recommended dtype for Apple Silicon
+torch_dtype = torch.bfloat16  # Better than float16 on Apple Silicon
+
+# Attention slicing often helps on MPS
+pipe.enable_attention_slicing()
+```
+
+### CPU Optimizations
+```python
+# Use float32 for CPU
+torch_dtype = torch.float32
+
+# Enable optimized attention
+pipe.enable_attention_slicing()
+```
+
+## Model-Specific Guidelines
+
+### FLUX Models
+- Do NOT use guidance_scale parameter (not needed for FLUX)
+- Use 4-8 inference steps maximum
+- BF16 dtype recommended
+- Enable attention slicing for memory optimization
+
+### Stable Diffusion XL
+- Enable attention slicing for high resolutions
+- Use refiner model sparingly to save memory
+- Consider VAE tiling for >1024px images
+
+### Stable Diffusion 1.5/2.1
+- Very memory efficient base models
+- Can often run without optimizations on 8GB+ VRAM
+- Enable VAE slicing for batch processing
+
+## Memory Usage Estimation
+- FLUX.1: ~24GB for full precision, ~12GB for FP16
+- SDXL: ~7GB for FP16, ~14GB for FP32
+- SD 1.5: ~2GB for FP16, ~4GB for FP32
+
+## Optimization Combinations by VRAM
+
+### 24GB+ VRAM (High-end)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+pipe = pipe.to("cuda")
+pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+```
+
+### 12-24GB VRAM (Mid-range)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+pipe.enable_model_cpu_offload()
+pipe.enable_xformers_memory_efficient_attention()
+```
+
+### 8-12GB VRAM (Entry-level)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe.enable_sequential_cpu_offload()
+pipe.enable_attention_slicing()
+pipe.enable_vae_slicing()
+pipe.enable_xformers_memory_efficient_attention()
+```
+
+### <8GB VRAM (Low-end)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe.enable_sequential_cpu_offload()
+pipe.enable_attention_slicing("max")
+pipe.enable_vae_slicing()
+pipe.enable_vae_tiling()
+```
+
+
+IMPORTANT: For FLUX.1-schnell models, do NOT include guidance_scale parameter as it's not needed.
+
+Using the OPTIMIZATION KNOWLEDGE BASE above, generate Python code that:
+
+1. **Selects the best optimization techniques** for the specific hardware profile
+2. **Applies appropriate memory optimizations** based on available VRAM
+3. **Uses optimal data types** for the target hardware:
+   - User specified dtype (if provided): Use exactly as specified
+   - Apple Silicon (MPS): prefer torch.bfloat16
+   - NVIDIA GPUs: prefer torch.float16 or torch.bfloat16 
+   - CPU only: use torch.float32
+4. **Implements hardware-specific optimizations** (CUDA, MPS, CPU)
+5. **Follows model-specific guidelines** (e.g., FLUX guidance_scale handling)
+
+IMPORTANT GUIDELINES:
+- Reference the OPTIMIZATION KNOWLEDGE BASE to select appropriate techniques
+- Include all necessary imports
+- Add brief comments explaining optimization choices
+- Generate compact, production-ready code
+- Inline values where possible for concise code
+- Generate ONLY the Python code, no explanations before or after the code block
+
+2025-05-30 00:30:05,726 - auto_diffusers - INFO - ================================================================================
+2025-05-30 00:30:05,726 - auto_diffusers - INFO - Sending request to Gemini API
+2025-05-30 00:30:17,996 - auto_diffusers - INFO - Successfully received response from Gemini API (no tools used)
+2025-05-30 00:30:17,997 - auto_diffusers - DEBUG - Response length: 2079 characters
+2025-05-30 00:33:31,874 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:33:31,874 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:33:31,874 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:33:31,874 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:33:31,874 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:33:31,874 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:33:31,874 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:33:31,874 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:33:31,874 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:33:31,874 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:33:31,879 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:33:31,879 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:33:32,357 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:33:32,357 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:33:32,357 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:33:32,357 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:33:32,357 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:33:32,357 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:33:32,357 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:33:32,357 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:33:32,357 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:33:32,357 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:33:32,357 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:33:32,359 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:33:32,371 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:33:32,371 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:33:32,465 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:33:32,498 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:33:32,498 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x141269990>
+2025-05-30 00:33:32,498 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:33:32,499 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:33:32,499 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:33:32,499 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:33:32,499 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:33:32,499 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:33:32 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:33:32,499 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:33:32,500 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:33:32,500 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:33:32,500 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:33:32,500 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:33:32,500 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:33:32,500 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:33:32,500 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:33:32,500 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x142f3b290>
+2025-05-30 00:33:32,500 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:33:32,501 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:33:32,501 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:33:32,501 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:33:32,501 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:33:32,507 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:33:32 GMT'), (b'server', b'uvicorn'), (b'content-length', b'105814'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:33:32,507 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:33:32,507 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:33:32,507 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:33:32,507 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:33:32,507 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:33:32,507 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:33:32,507 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:33:32,517 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:33:32,537 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x14126bf90>
+2025-05-30 00:33:32,537 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x131724f80> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:33:32,654 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x142dbc510>
+2025-05-30 00:33:32,654 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x142dcbf50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:33:32,677 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:33:32,813 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1412c8650>
+2025-05-30 00:33:32,813 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:33:32,813 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:33:32,813 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:33:32,813 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:33:32,813 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:33:32,928 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x141212010>
+2025-05-30 00:33:32,929 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:33:32,929 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:33:32,929 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:33:32,929 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:33:32,929 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:33:32,955 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:33:32 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:33:32,955 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:33:32,955 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:33:32,955 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:33:32,955 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:33:32,955 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:33:32,955 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:33:32,956 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:33:33,068 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:33:33 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:33:33,069 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:33:33,069 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:33:33,069 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:33:33,069 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:33:33,069 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:33:33,069 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:33:33,069 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:33:33,701 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:33:33,917 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:33:34,332 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:33:34,332 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:33:34,332 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:33:34,332 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:33:34,333 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:33:34,333 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:33:34,333 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:33:34,333 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:33:34,333 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:33:38,242 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:33:38,242 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:33:38,242 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:33:38,242 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:33:38,242 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:33:38,243 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:33:38,243 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:33:38,243 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:33:38,243 - auto_diffusers - INFO - Starting code generation for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:33:38,243 - auto_diffusers - DEBUG - Parameters: prompt='A cat holding a sign that says hello world...', size=(768, 1360), steps=4
+2025-05-30 00:33:38,243 - auto_diffusers - DEBUG - Manual specs: True, Memory analysis provided: True
+2025-05-30 00:33:38,243 - auto_diffusers - INFO - Using manual hardware specifications
+2025-05-30 00:33:38,243 - auto_diffusers - DEBUG - Manual specs: {'platform': 'Linux', 'architecture': 'manual_input', 'cpu_count': 8, 'python_version': '3.11', 'cuda_available': False, 'mps_available': False, 'torch_version': '2.0+', 'manual_input': True, 'ram_gb': 16, 'user_dtype': None, 'gpu_info': None}
+2025-05-30 00:33:38,243 - auto_diffusers - INFO - No GPU detected, using CPU-only profile
+2025-05-30 00:33:38,243 - auto_diffusers - INFO - Selected optimization profile: cpu_only
+2025-05-30 00:33:38,243 - auto_diffusers - DEBUG - Creating generation prompt for Gemini API
+2025-05-30 00:33:38,243 - auto_diffusers - DEBUG - Prompt length: 7566 characters
+2025-05-30 00:33:38,243 - auto_diffusers - INFO - ================================================================================
+2025-05-30 00:33:38,243 - auto_diffusers - INFO - PROMPT SENT TO GEMINI API:
+2025-05-30 00:33:38,243 - auto_diffusers - INFO - ================================================================================
+2025-05-30 00:33:38,243 - auto_diffusers - INFO - 
+You are an expert in optimizing diffusers library code for different hardware configurations.
+
+NOTE: This system includes curated optimization knowledge from HuggingFace documentation.
+
+TASK: Generate optimized Python code for running a diffusion model with the following specifications:
+- Model: black-forest-labs/FLUX.1-schnell
+- Prompt: "A cat holding a sign that says hello world"
+- Image size: 768x1360
+- Inference steps: 4
+
+HARDWARE SPECIFICATIONS:
+- Platform: Linux (manual_input)
+- CPU Cores: 8
+- CUDA Available: False
+- MPS Available: False
+- Optimization Profile: cpu_only
+
+MEMORY ANALYSIS:
+- Model Memory Requirements: 36.0 GB (FP16 inference)
+- Model Weights Size: 24.0 GB (FP16)
+- Memory Recommendation: 🔄 Requires sequential CPU offloading
+- Recommended Precision: float16
+- Attention Slicing Recommended: True
+- VAE Slicing Recommended: True
+
+OPTIMIZATION KNOWLEDGE BASE:
+
+# DIFFUSERS OPTIMIZATION TECHNIQUES
+
+## Memory Optimization Techniques
+
+### 1. Model CPU Offloading
+Use `enable_model_cpu_offload()` to move models between GPU and CPU automatically:
+```python
+pipe.enable_model_cpu_offload()
+```
+- Saves significant VRAM by keeping only active models on GPU
+- Automatic management, no manual intervention needed
+- Compatible with all pipelines
+
+### 2. Sequential CPU Offloading  
+Use `enable_sequential_cpu_offload()` for more aggressive memory saving:
+```python
+pipe.enable_sequential_cpu_offload()
+```
+- More memory efficient than model offloading
+- Moves models to CPU after each forward pass
+- Best for very limited VRAM scenarios
+
+### 3. Attention Slicing
+Use `enable_attention_slicing()` to reduce memory during attention computation:
+```python
+pipe.enable_attention_slicing()
+# or specify slice size
+pipe.enable_attention_slicing("max")  # maximum slicing
+pipe.enable_attention_slicing(1)      # slice_size = 1
+```
+- Trades compute time for memory
+- Most effective for high-resolution images
+- Can be combined with other techniques
+
+### 4. VAE Slicing
+Use `enable_vae_slicing()` for large batch processing:
+```python
+pipe.enable_vae_slicing()
+```
+- Decodes images one at a time instead of all at once
+- Essential for batch sizes > 4
+- Minimal performance impact on single images
+
+### 5. VAE Tiling
+Use `enable_vae_tiling()` for high-resolution image generation:
+```python
+pipe.enable_vae_tiling()
+```
+- Enables 4K+ image generation on 8GB VRAM
+- Splits images into overlapping tiles
+- Automatically disabled for 512x512 or smaller images
+
+### 6. Memory Efficient Attention (xFormers)
+Use `enable_xformers_memory_efficient_attention()` if xFormers is installed:
+```python
+pipe.enable_xformers_memory_efficient_attention()
+```
+- Significantly reduces memory usage and improves speed
+- Requires xformers library installation
+- Compatible with most models
+
+## Performance Optimization Techniques
+
+### 1. Half Precision (FP16/BF16)
+Use lower precision for better memory and speed:
+```python
+# FP16 (widely supported)
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+
+# BF16 (better numerical stability, newer hardware)
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+```
+- FP16: Halves memory usage, widely supported
+- BF16: Better numerical stability, requires newer GPUs
+- Essential for most optimization scenarios
+
+### 2. Torch Compile (PyTorch 2.0+)
+Use `torch.compile()` for significant speed improvements:
+```python
+pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+# For some models, compile VAE too:
+pipe.vae.decode = torch.compile(pipe.vae.decode, mode="reduce-overhead", fullgraph=True)
+```
+- 5-50% speed improvement
+- Requires PyTorch 2.0+
+- First run is slower due to compilation
+
+### 3. Fast Schedulers
+Use faster schedulers for fewer steps:
+```python
+from diffusers import LMSDiscreteScheduler, UniPCMultistepScheduler
+
+# LMS Scheduler (good quality, fast)
+pipe.scheduler = LMSDiscreteScheduler.from_config(pipe.scheduler.config)
+
+# UniPC Scheduler (fastest)
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+```
+
+## Hardware-Specific Optimizations
+
+### NVIDIA GPU Optimizations
+```python
+# Enable Tensor Cores
+torch.backends.cudnn.benchmark = True
+
+# Optimal data type for NVIDIA
+torch_dtype = torch.float16  # or torch.bfloat16 for RTX 30/40 series
+```
+
+### Apple Silicon (MPS) Optimizations
+```python
+# Use MPS device
+device = "mps" if torch.backends.mps.is_available() else "cpu"
+pipe = pipe.to(device)
+
+# Recommended dtype for Apple Silicon
+torch_dtype = torch.bfloat16  # Better than float16 on Apple Silicon
+
+# Attention slicing often helps on MPS
+pipe.enable_attention_slicing()
+```
+
+### CPU Optimizations
+```python
+# Use float32 for CPU
+torch_dtype = torch.float32
+
+# Enable optimized attention
+pipe.enable_attention_slicing()
+```
+
+## Model-Specific Guidelines
+
+### FLUX Models
+- Do NOT use guidance_scale parameter (not needed for FLUX)
+- Use 4-8 inference steps maximum
+- BF16 dtype recommended
+- Enable attention slicing for memory optimization
+
+### Stable Diffusion XL
+- Enable attention slicing for high resolutions
+- Use refiner model sparingly to save memory
+- Consider VAE tiling for >1024px images
+
+### Stable Diffusion 1.5/2.1
+- Very memory efficient base models
+- Can often run without optimizations on 8GB+ VRAM
+- Enable VAE slicing for batch processing
+
+## Memory Usage Estimation
+- FLUX.1: ~24GB for full precision, ~12GB for FP16
+- SDXL: ~7GB for FP16, ~14GB for FP32
+- SD 1.5: ~2GB for FP16, ~4GB for FP32
+
+## Optimization Combinations by VRAM
+
+### 24GB+ VRAM (High-end)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+pipe = pipe.to("cuda")
+pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+```
+
+### 12-24GB VRAM (Mid-range)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+pipe.enable_model_cpu_offload()
+pipe.enable_xformers_memory_efficient_attention()
+```
+
+### 8-12GB VRAM (Entry-level)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe.enable_sequential_cpu_offload()
+pipe.enable_attention_slicing()
+pipe.enable_vae_slicing()
+pipe.enable_xformers_memory_efficient_attention()
+```
+
+### <8GB VRAM (Low-end)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe.enable_sequential_cpu_offload()
+pipe.enable_attention_slicing("max")
+pipe.enable_vae_slicing()
+pipe.enable_vae_tiling()
+```
+
+
+IMPORTANT: For FLUX.1-schnell models, do NOT include guidance_scale parameter as it's not needed.
+
+Using the OPTIMIZATION KNOWLEDGE BASE above, generate Python code that:
+
+1. **Selects the best optimization techniques** for the specific hardware profile
+2. **Applies appropriate memory optimizations** based on available VRAM
+3. **Uses optimal data types** for the target hardware:
+   - User specified dtype (if provided): Use exactly as specified
+   - Apple Silicon (MPS): prefer torch.bfloat16
+   - NVIDIA GPUs: prefer torch.float16 or torch.bfloat16 
+   - CPU only: use torch.float32
+4. **Implements hardware-specific optimizations** (CUDA, MPS, CPU)
+5. **Follows model-specific guidelines** (e.g., FLUX guidance_scale handling)
+
+IMPORTANT GUIDELINES:
+- Reference the OPTIMIZATION KNOWLEDGE BASE to select appropriate techniques
+- Include all necessary imports
+- Add brief comments explaining optimization choices
+- Generate compact, production-ready code
+- Inline values where possible for concise code
+- Generate ONLY the Python code, no explanations before or after the code block
+
+2025-05-30 00:33:38,244 - auto_diffusers - INFO - ================================================================================
+2025-05-30 00:33:38,244 - auto_diffusers - INFO - Sending request to Gemini API
+2025-05-30 00:33:51,592 - auto_diffusers - INFO - Successfully received response from Gemini API (no tools used)
+2025-05-30 00:33:51,593 - auto_diffusers - DEBUG - Response length: 1708 characters
+2025-05-30 00:36:05,006 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:36:05,006 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:36:05,006 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:36:05,006 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:36:05,006 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:36:05,006 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:36:05,006 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:36:05,006 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:36:05,006 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:36:05,006 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:36:05,009 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:36:05,009 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:36:05,422 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:36:05,422 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:36:05,422 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:36:05,422 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:36:05,422 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:36:05,422 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:36:05,422 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:36:05,422 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:36:05,422 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:36:05,422 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:36:05,422 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:36:05,424 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:36:05,437 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:36:05,442 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:36:05,513 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:36:05,548 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:36:05,548 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x125f2b3d0>
+2025-05-30 00:36:05,548 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:36:05,548 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:36:05,549 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:36:05,549 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:36:05,549 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:36:05,549 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:36:05 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:36:05,549 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:36:05,549 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:36:05,549 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:36:05,549 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:36:05,549 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:36:05,549 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:36:05,550 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:36:05,550 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:36:05,550 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x127813610>
+2025-05-30 00:36:05,550 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:36:05,550 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:36:05,550 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:36:05,551 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:36:05,551 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:36:05,557 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:36:05 GMT'), (b'server', b'uvicorn'), (b'content-length', b'105805'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:36:05,557 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:36:05,557 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:36:05,557 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:36:05,557 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:36:05,557 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:36:05,557 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:36:05,557 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:36:05,568 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:36:05,681 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x125fa5a50>
+2025-05-30 00:36:05,681 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x115224f80> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:36:05,718 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1255b6bd0>
+2025-05-30 00:36:05,718 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x126fcbf50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:36:05,734 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:36:05,966 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x127906b90>
+2025-05-30 00:36:05,966 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:36:05,967 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:36:05,967 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:36:05,967 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:36:05,967 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:36:06,020 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1253d6ed0>
+2025-05-30 00:36:06,020 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:36:06,020 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:36:06,020 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:36:06,021 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:36:06,021 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:36:06,109 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:36:06 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:36:06,110 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:36:06,110 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:36:06,110 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:36:06,110 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:36:06,110 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:36:06,110 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:36:06,110 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:36:06,172 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:36:06 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:36:06,172 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:36:06,172 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:36:06,172 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:36:06,172 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:36:06,172 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:36:06,172 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:36:06,172 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:36:06,788 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:36:07,005 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:36:25,970 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:36:25,971 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:36:25,971 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:36:25,971 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:36:25,971 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:36:25,971 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:36:25,971 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:36:25,971 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:36:25,972 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:41:24,618 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:41:24,618 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:41:24,618 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:41:24,618 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:41:24,618 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:41:24,618 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:41:24,618 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:41:24,618 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:41:24,618 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:41:24,618 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:41:24,622 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:41:24,623 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:41:25,060 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:41:25,060 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:41:25,060 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:41:25,060 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:41:25,060 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:41:25,060 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:41:25,060 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:41:25,060 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:41:25,060 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:41:25,060 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:41:25,060 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:41:25,062 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:41:25,076 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:41:25,082 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:41:25,164 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:41:25,195 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:41:25,196 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12d73da90>
+2025-05-30 00:41:25,196 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:41:25,196 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:41:25,196 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:41:25,197 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:41:25,197 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:41:25,197 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:41:25 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:41:25,197 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:41:25,197 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:41:25,197 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:41:25,197 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:41:25,197 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:41:25,197 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:41:25,197 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:41:25,198 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:41:25,198 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12d941150>
+2025-05-30 00:41:25,198 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:41:25,198 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:41:25,198 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:41:25,198 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:41:25,198 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:41:25,205 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:41:25 GMT'), (b'server', b'uvicorn'), (b'content-length', b'104937'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:41:25,206 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:41:25,206 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:41:25,206 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:41:25,206 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:41:25,206 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:41:25,206 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:41:25,206 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:41:25,217 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:41:25,326 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12d39c990>
+2025-05-30 00:41:25,326 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x12cf8d760> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:41:25,367 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:41:25,371 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12d7b6410>
+2025-05-30 00:41:25,372 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x12d7c7f50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:41:25,608 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12c6b7810>
+2025-05-30 00:41:25,608 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:41:25,609 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:41:25,609 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:41:25,609 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:41:25,609 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:41:25,681 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12c60d010>
+2025-05-30 00:41:25,682 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:41:25,682 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:41:25,682 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:41:25,682 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:41:25,682 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:41:25,750 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:41:25 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:41:25,751 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:41:25,751 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:41:25,751 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:41:25,751 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:41:25,751 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:41:25,751 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:41:25,751 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:41:25,839 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:41:25 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:41:25,840 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:41:25,840 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:41:25,841 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:41:25,841 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:41:25,841 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:41:25,841 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:41:25,841 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:41:26,445 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:41:26,683 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:41:27,126 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:41:27,127 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:41:27,127 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:41:27,127 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:41:27,127 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:41:27,127 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:41:27,127 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:41:27,128 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:41:27,128 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:41:28,862 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:41:28,863 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:41:28,863 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:41:28,863 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:41:28,863 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:41:28,863 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:41:28,863 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:41:28,863 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:41:30,138 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:41:30,139 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:41:30,139 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:41:30,139 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:41:30,139 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:41:30,139 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:41:30,139 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:41:30,140 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:43:45,643 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:43:45,643 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:43:45,643 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:43:45,643 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:43:45,644 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:43:45,644 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:43:45,644 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:43:45,644 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:43:45,644 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:43:45,644 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:43:45,647 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:43:45,647 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:43:46,100 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:43:46,100 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:43:46,100 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:43:46,100 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:43:46,100 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:43:46,100 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:43:46,100 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:43:46,100 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:43:46,100 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:43:46,100 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:43:46,100 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:43:46,103 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:43:46,116 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:43:46,120 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:43:46,191 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:43:46,228 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:43:46,228 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1262b3c90>
+2025-05-30 00:43:46,228 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:43:46,229 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:43:46,229 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:43:46,229 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:43:46,229 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:43:46,229 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:43:46 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:43:46,229 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:43:46,229 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:43:46,230 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:43:46,230 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:43:46,230 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:43:46,230 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:43:46,230 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:43:46,230 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:43:46,230 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x135b19290>
+2025-05-30 00:43:46,230 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:43:46,231 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:43:46,231 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:43:46,231 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:43:46,231 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:43:46,237 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:43:46 GMT'), (b'server', b'uvicorn'), (b'content-length', b'105071'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:43:46,237 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:43:46,237 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:43:46,237 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:43:46,237 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:43:46,237 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:43:46,237 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:43:46,237 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:43:46,247 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:43:46,317 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x131abcf50>
+2025-05-30 00:43:46,317 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x114824f80> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:43:46,384 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x135a2ec90>
+2025-05-30 00:43:46,384 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x132ec7f50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:43:46,394 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:43:46,603 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x130d83a50>
+2025-05-30 00:43:46,604 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:43:46,604 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:43:46,605 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:43:46,605 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:43:46,605 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:43:46,659 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x132e478d0>
+2025-05-30 00:43:46,660 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:43:46,660 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:43:46,661 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:43:46,661 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:43:46,661 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:43:46,753 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:43:46 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:43:46,753 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:43:46,754 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:43:46,754 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:43:46,754 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:43:46,754 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:43:46,754 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:43:46,755 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:43:46,800 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:43:46 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:43:46,800 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:43:46,800 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:43:46,801 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:43:46,801 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:43:46,801 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:43:46,801 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:43:46,801 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:43:47,349 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:43:47,349 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:43:47,349 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:43:47,349 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:43:47,349 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:43:47,349 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:43:47,350 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:43:47,350 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:43:47,350 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:43:47,379 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:43:47,604 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:45:54,947 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:45:54,947 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:45:54,947 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:45:54,947 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:45:54,947 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:45:54,947 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:45:54,947 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:45:54,947 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:45:54,947 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:45:54,947 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:45:54,950 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:45:54,950 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:45:55,354 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:45:55,354 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:45:55,354 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:45:55,354 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:45:55,354 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:45:55,354 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:45:55,354 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:45:55,354 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:45:55,354 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:45:55,354 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:45:55,354 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:45:55,356 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:45:55,369 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:45:55,374 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:45:55,445 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:45:55,480 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:45:55,480 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x13009d9d0>
+2025-05-30 00:45:55,480 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:45:55,481 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:45:55,481 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:45:55,481 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:45:55,481 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:45:55,481 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:45:55 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:45:55,482 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:45:55,482 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:45:55,482 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:45:55,482 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:45:55,482 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:45:55,482 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:45:55,482 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:45:55,482 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:45:55,483 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x13040d250>
+2025-05-30 00:45:55,483 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:45:55,483 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:45:55,483 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:45:55,483 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:45:55,483 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:45:55,489 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:45:55 GMT'), (b'server', b'uvicorn'), (b'content-length', b'103733'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:45:55,489 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:45:55,489 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:45:55,489 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:45:55,489 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:45:55,489 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:45:55,489 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:45:55,489 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:45:55,500 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:45:55,532 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1258af790>
+2025-05-30 00:45:55,532 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x12548d6d0> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:45:55,637 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x130401610>
+2025-05-30 00:45:55,638 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x1301c7ec0> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:45:55,646 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:45:55,812 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x123b1b390>
+2025-05-30 00:45:55,812 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:45:55,812 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:45:55,812 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:45:55,812 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:45:55,812 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:45:55,912 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1250abdd0>
+2025-05-30 00:45:55,913 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:45:55,913 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:45:55,913 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:45:55,913 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:45:55,913 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:45:55,954 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:45:55 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:45:55,954 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:45:55,954 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:45:55,954 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:45:55,955 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:45:55,955 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:45:55,955 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:45:55,955 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:45:56,053 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:45:55 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:45:56,054 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:45:56,054 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:45:56,055 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:45:56,055 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:45:56,055 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:45:56,055 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:45:56,056 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:45:56,657 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:45:56,876 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:45:58,569 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:45:58,569 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:45:58,569 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:45:58,569 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:45:58,569 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:45:58,569 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:45:58,569 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:45:58,570 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:45:58,570 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:47:58,681 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:47:58,682 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:47:58,682 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:47:58,682 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:47:58,682 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:47:58,682 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:47:58,682 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:47:58,682 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:47:58,682 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:47:58,682 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:47:58,685 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:47:58,685 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:47:59,088 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:47:59,088 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:47:59,088 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:47:59,088 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:47:59,088 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:47:59,088 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:47:59,088 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:47:59,088 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:47:59,089 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:47:59,089 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:47:59,089 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:47:59,091 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:47:59,104 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:47:59,109 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:47:59,179 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:47:59,214 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:47:59,215 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11fb004d0>
+2025-05-30 00:47:59,215 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:47:59,215 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:47:59,215 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:47:59,215 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:47:59,216 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:47:59,216 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:47:59 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:47:59,216 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:47:59,216 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:47:59,216 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:47:59,216 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:47:59,216 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:47:59,216 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:47:59,216 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:47:59,217 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:47:59,217 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11fb155d0>
+2025-05-30 00:47:59,217 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:47:59,217 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:47:59,217 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:47:59,217 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:47:59,217 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:47:59,223 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:47:59 GMT'), (b'server', b'uvicorn'), (b'content-length', b'103526'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:47:59,224 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:47:59,224 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:47:59,224 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:47:59,224 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:47:59,224 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:47:59,224 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:47:59,224 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:47:59,235 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:47:59,375 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:47:59,424 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11d8f2b10>
+2025-05-30 00:47:59,424 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x11f9c7f50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:47:59,426 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11e387f90>
+2025-05-30 00:47:59,426 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x10da25010> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:47:59,699 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11dd27350>
+2025-05-30 00:47:59,699 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:47:59,700 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:47:59,700 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:47:59,700 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:47:59,700 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:47:59,705 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11b6a4910>
+2025-05-30 00:47:59,705 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:47:59,706 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:47:59,706 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:47:59,706 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:47:59,707 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:47:59,840 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:47:59 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:47:59,841 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:47:59,841 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:47:59,842 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:47:59,842 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:47:59,842 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:47:59,843 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:47:59,843 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:47:59,854 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:47:59 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:47:59,856 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:47:59,856 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:47:59,856 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:47:59,856 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:47:59,856 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:47:59,857 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:47:59,857 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:48:00,536 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:48:00,763 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:48:01,404 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:48:01,404 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:48:01,404 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:48:01,404 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:48:01,404 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:48:01,404 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:48:01,404 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:48:01,404 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:48:01,404 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:49:30,798 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:49:30,798 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:49:30,798 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:49:30,798 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:49:30,798 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:49:30,798 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:49:30,798 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:49:30,798 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:49:30,798 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:49:30,798 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:49:30,803 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:49:30,803 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:49:31,302 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:49:31,302 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:49:31,302 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:49:31,302 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:49:31,302 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:49:31,302 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:49:31,302 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:49:31,302 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:49:31,302 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:49:31,302 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:49:31,302 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:49:31,304 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:49:31,318 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:49:31,323 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:49:31,393 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:49:31,429 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:49:31,429 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x16b22a310>
+2025-05-30 00:49:31,429 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:49:31,429 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:49:31,429 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:49:31,430 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:49:31,430 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:49:31,430 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:49:31 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:49:31,430 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:49:31,430 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:49:31,430 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:49:31,430 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:49:31,430 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:49:31,430 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:49:31,430 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:49:31,431 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:49:31,431 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x16b6158d0>
+2025-05-30 00:49:31,431 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:49:31,431 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:49:31,431 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:49:31,431 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:49:31,431 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:49:31,437 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:49:31 GMT'), (b'server', b'uvicorn'), (b'content-length', b'102528'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:49:31,437 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:49:31,438 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:49:31,438 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:49:31,438 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:49:31,438 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:49:31,438 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:49:31,438 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:49:31,448 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:49:31,483 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x16935b110>
+2025-05-30 00:49:31,483 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x16918d6d0> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:49:31,588 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x16b69e1d0>
+2025-05-30 00:49:31,588 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x16b2cfda0> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:49:31,648 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:49:31,769 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1687e7b10>
+2025-05-30 00:49:31,770 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:49:31,770 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:49:31,771 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:49:31,771 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:49:31,771 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:49:31,957 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:49:31 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:49:31,958 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x16873c610>
+2025-05-30 00:49:31,959 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:49:31,959 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:49:31,959 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:49:31,960 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:49:31,960 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:49:31,960 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:49:31,960 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:49:31,960 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:49:31,960 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:49:31,961 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:49:31,961 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:49:31,961 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:49:32,105 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:49:32 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:49:32,106 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:49:32,106 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:49:32,107 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:49:32,107 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:49:32,107 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:49:32,107 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:49:32,108 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:49:32,646 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:49:32,647 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:49:32,647 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:49:32,647 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:49:32,647 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:49:32,647 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:49:32,647 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:49:32,647 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:49:32,647 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:49:32,765 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:49:33,005 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:53:47,386 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 00:53:47,386 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 00:53:47,386 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 00:53:47,386 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 00:53:47,386 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 00:53:47,386 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 00:53:47,386 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 00:53:47,386 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 00:53:47,386 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 00:53:47,386 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 00:53:47,392 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 00:53:47,392 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 00:53:47,845 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 00:53:47,845 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 00:53:47,845 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 00:53:47,845 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 00:53:47,845 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 00:53:47,845 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 00:53:47,845 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 00:53:47,845 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 00:53:47,845 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 00:53:47,845 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 00:53:47,845 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 00:53:47,847 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:53:47,861 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 00:53:47,861 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:53:47,946 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 00:53:47,981 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 00:53:47,982 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x12118e7d0>
+2025-05-30 00:53:47,982 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:53:47,983 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:53:47,985 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:53:47,985 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:53:47,985 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:53:47,985 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:53:47 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 00:53:47,986 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 00:53:47,986 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:53:47,986 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:53:47,986 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:53:47,986 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:53:47,986 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:53:47,986 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:53:47,986 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 00:53:47,987 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x127ced450>
+2025-05-30 00:53:47,987 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:53:47,987 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:53:47,987 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 00:53:47,987 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:53:47,988 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 00:53:47,994 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 15:53:47 GMT'), (b'server', b'uvicorn'), (b'content-length', b'95944'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 00:53:47,994 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 00:53:47,994 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 00:53:47,994 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:53:47,994 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:53:47,994 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:53:47,994 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:53:47,994 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:53:48,005 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 00:53:48,021 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1259a4b50>
+2025-05-30 00:53:48,022 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x12558d5b0> server_hostname='api.gradio.app' timeout=3
+2025-05-30 00:53:48,142 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1278d7850>
+2025-05-30 00:53:48,142 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x1279cbe30> server_hostname='api.gradio.app' timeout=30
+2025-05-30 00:53:48,149 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 00:53:48,296 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x125941710>
+2025-05-30 00:53:48,296 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:53:48,297 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:53:48,297 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:53:48,297 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:53:48,297 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:53:48,420 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x127844250>
+2025-05-30 00:53:48,420 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 00:53:48,420 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 00:53:48,420 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 00:53:48,420 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 00:53:48,420 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 00:53:48,434 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:53:48 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 00:53:48,435 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 00:53:48,435 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:53:48,435 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:53:48,435 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:53:48,435 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:53:48,436 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:53:48,436 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:53:48,560 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 15:53:48 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 00:53:48,561 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 00:53:48,562 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 00:53:48,562 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 00:53:48,563 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 00:53:48,563 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 00:53:48,563 - httpcore.connection - DEBUG - close.started
+2025-05-30 00:53:48,563 - httpcore.connection - DEBUG - close.complete
+2025-05-30 00:53:49,159 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 00:53:49,382 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 00:56:51,723 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:56:51,724 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:56:51,724 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 00:56:51,724 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 00:56:51,725 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:56:51,725 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 00:56:51,725 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 00:56:51,725 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 00:56:51,725 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:36,891 - __main__ - INFO - Initializing GradioAutodiffusers
+2025-05-30 01:00:36,891 - __main__ - DEBUG - API key found, length: 39
+2025-05-30 01:00:36,891 - auto_diffusers - INFO - Initializing AutoDiffusersGenerator
+2025-05-30 01:00:36,891 - auto_diffusers - DEBUG - API key length: 39
+2025-05-30 01:00:36,891 - auto_diffusers - WARNING - Tool calling dependencies not available, running without tools
+2025-05-30 01:00:36,891 - hardware_detector - INFO - Initializing HardwareDetector
+2025-05-30 01:00:36,891 - hardware_detector - DEBUG - Starting system hardware detection
+2025-05-30 01:00:36,891 - hardware_detector - DEBUG - Platform: Darwin, Architecture: arm64
+2025-05-30 01:00:36,891 - hardware_detector - DEBUG - CPU cores: 16, Python: 3.11.11
+2025-05-30 01:00:36,891 - hardware_detector - DEBUG - Attempting GPU detection via nvidia-smi
+2025-05-30 01:00:36,895 - hardware_detector - DEBUG - nvidia-smi not found, no NVIDIA GPU detected
+2025-05-30 01:00:36,895 - hardware_detector - DEBUG - Checking PyTorch availability
+2025-05-30 01:00:37,384 - hardware_detector - INFO - PyTorch 2.7.0 detected
+2025-05-30 01:00:37,384 - hardware_detector - DEBUG - CUDA available: False, MPS available: True
+2025-05-30 01:00:37,384 - hardware_detector - INFO - Hardware detection completed successfully
+2025-05-30 01:00:37,384 - hardware_detector - DEBUG - Detected specs: {'platform': 'Darwin', 'architecture': 'arm64', 'cpu_count': 16, 'python_version': '3.11.11', 'gpu_info': None, 'cuda_available': False, 'mps_available': True, 'torch_version': '2.7.0'}
+2025-05-30 01:00:37,384 - auto_diffusers - INFO - Hardware detector initialized successfully
+2025-05-30 01:00:37,384 - __main__ - INFO - AutoDiffusersGenerator initialized successfully
+2025-05-30 01:00:37,384 - simple_memory_calculator - INFO - Initializing SimpleMemoryCalculator
+2025-05-30 01:00:37,384 - simple_memory_calculator - DEBUG - HuggingFace API initialized
+2025-05-30 01:00:37,384 - simple_memory_calculator - DEBUG - Known models in database: 4
+2025-05-30 01:00:37,384 - __main__ - INFO - SimpleMemoryCalculator initialized successfully
+2025-05-30 01:00:37,384 - __main__ - DEBUG - Default model settings: gemini-2.5-flash-preview-05-20, temp=0.7
+2025-05-30 01:00:37,386 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 01:00:37,399 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=3 socket_options=None
+2025-05-30 01:00:37,399 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 01:00:37,476 - asyncio - DEBUG - Using selector: KqueueSelector
+2025-05-30 01:00:37,512 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=None socket_options=None
+2025-05-30 01:00:37,512 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11f6c6290>
+2025-05-30 01:00:37,513 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 01:00:37,513 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 01:00:37,513 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 01:00:37,513 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 01:00:37,513 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 01:00:37,513 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 16:00:37 GMT'), (b'server', b'uvicorn'), (b'content-length', b'4'), (b'content-type', b'application/json')])
+2025-05-30 01:00:37,513 - httpx - INFO - HTTP Request: GET http://localhost:7861/gradio_api/startup-events "HTTP/1.1 200 OK"
+2025-05-30 01:00:37,514 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 01:00:37,514 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 01:00:37,514 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 01:00:37,514 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 01:00:37,514 - httpcore.connection - DEBUG - close.started
+2025-05-30 01:00:37,514 - httpcore.connection - DEBUG - close.complete
+2025-05-30 01:00:37,514 - httpcore.connection - DEBUG - connect_tcp.started host='localhost' port=7861 local_address=None timeout=3 socket_options=None
+2025-05-30 01:00:37,515 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11f7f06d0>
+2025-05-30 01:00:37,515 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'HEAD']>
+2025-05-30 01:00:37,515 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 01:00:37,515 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'HEAD']>
+2025-05-30 01:00:37,515 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 01:00:37,515 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'HEAD']>
+2025-05-30 01:00:37,521 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'date', b'Thu, 29 May 2025 16:00:37 GMT'), (b'server', b'uvicorn'), (b'content-length', b'95123'), (b'content-type', b'text/html; charset=utf-8')])
+2025-05-30 01:00:37,521 - httpx - INFO - HTTP Request: HEAD http://localhost:7861/ "HTTP/1.1 200 OK"
+2025-05-30 01:00:37,521 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'HEAD']>
+2025-05-30 01:00:37,521 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 01:00:37,521 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 01:00:37,521 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 01:00:37,521 - httpcore.connection - DEBUG - close.started
+2025-05-30 01:00:37,521 - httpcore.connection - DEBUG - close.complete
+2025-05-30 01:00:37,532 - httpcore.connection - DEBUG - connect_tcp.started host='api.gradio.app' port=443 local_address=None timeout=30 socket_options=None
+2025-05-30 01:00:37,634 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x1064531d0>
+2025-05-30 01:00:37,635 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x10cd251c0> server_hostname='api.gradio.app' timeout=3
+2025-05-30 01:00:37,672 - httpcore.connection - DEBUG - connect_tcp.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11e2a82d0>
+2025-05-30 01:00:37,672 - httpcore.connection - DEBUG - start_tls.started ssl_context=<ssl.SSLContext object at 0x11f6c3f50> server_hostname='api.gradio.app' timeout=30
+2025-05-30 01:00:37,681 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/initiated HTTP/1.1" 200 0
+2025-05-30 01:00:37,911 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x11e274d90>
+2025-05-30 01:00:37,911 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 01:00:37,912 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 01:00:37,912 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 01:00:37,913 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 01:00:37,913 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 01:00:37,953 - httpcore.connection - DEBUG - start_tls.complete return_value=<httpcore._backends.sync.SyncStream object at 0x10e70cb90>
+2025-05-30 01:00:37,954 - httpcore.http11 - DEBUG - send_request_headers.started request=<Request [b'GET']>
+2025-05-30 01:00:37,955 - httpcore.http11 - DEBUG - send_request_headers.complete
+2025-05-30 01:00:37,955 - httpcore.http11 - DEBUG - send_request_body.started request=<Request [b'GET']>
+2025-05-30 01:00:37,955 - httpcore.http11 - DEBUG - send_request_body.complete
+2025-05-30 01:00:37,955 - httpcore.http11 - DEBUG - receive_response_headers.started request=<Request [b'GET']>
+2025-05-30 01:00:38,052 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 16:00:37 GMT'), (b'Content-Type', b'application/json'), (b'Content-Length', b'21'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'Access-Control-Allow-Origin', b'*')])
+2025-05-30 01:00:38,053 - httpx - INFO - HTTP Request: GET https://api.gradio.app/pkg-version "HTTP/1.1 200 OK"
+2025-05-30 01:00:38,054 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 01:00:38,054 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 01:00:38,055 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 01:00:38,055 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 01:00:38,055 - httpcore.connection - DEBUG - close.started
+2025-05-30 01:00:38,056 - httpcore.connection - DEBUG - close.complete
+2025-05-30 01:00:38,097 - httpcore.http11 - DEBUG - receive_response_headers.complete return_value=(b'HTTP/1.1', 200, b'OK', [(b'Date', b'Thu, 29 May 2025 16:00:38 GMT'), (b'Content-Type', b'text/html; charset=utf-8'), (b'Transfer-Encoding', b'chunked'), (b'Connection', b'keep-alive'), (b'Server', b'nginx/1.18.0'), (b'ContentType', b'application/json'), (b'Access-Control-Allow-Origin', b'*'), (b'Content-Encoding', b'gzip')])
+2025-05-30 01:00:38,098 - httpx - INFO - HTTP Request: GET https://api.gradio.app/v3/tunnel-request "HTTP/1.1 200 OK"
+2025-05-30 01:00:38,098 - httpcore.http11 - DEBUG - receive_response_body.started request=<Request [b'GET']>
+2025-05-30 01:00:38,099 - httpcore.http11 - DEBUG - receive_response_body.complete
+2025-05-30 01:00:38,099 - httpcore.http11 - DEBUG - response_closed.started
+2025-05-30 01:00:38,099 - httpcore.http11 - DEBUG - response_closed.complete
+2025-05-30 01:00:38,099 - httpcore.connection - DEBUG - close.started
+2025-05-30 01:00:38,100 - httpcore.connection - DEBUG - close.complete
+2025-05-30 01:00:38,699 - urllib3.connectionpool - DEBUG - Starting new HTTPS connection (1): huggingface.co:443
+2025-05-30 01:00:38,831 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:38,831 - simple_memory_calculator - INFO - Using known memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:38,832 - simple_memory_calculator - DEBUG - Known data: {'params_billions': 12.0, 'fp16_gb': 24.0, 'inference_fp16_gb': 36.0}
+2025-05-30 01:00:38,832 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 01:00:38,832 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:38,832 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:38,832 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 01:00:38,832 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:38,832 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:38,915 - urllib3.connectionpool - DEBUG - https://huggingface.co:443 "HEAD /api/telemetry/gradio/launched HTTP/1.1" 200 0
+2025-05-30 01:00:43,208 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:43,209 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:43,209 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 8.0GB VRAM
+2025-05-30 01:00:43,209 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:43,209 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:43,209 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 01:00:43,209 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:43,209 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:53,193 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:53,194 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:53,194 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 16.0GB VRAM
+2025-05-30 01:00:53,194 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:53,194 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:53,194 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 01:00:53,194 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:53,194 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:53,245 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:53,245 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:53,245 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 16.0GB VRAM
+2025-05-30 01:00:53,245 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:53,245 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:53,245 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 01:00:53,245 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 01:00:53,245 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 01:01:20,157 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 01:01:20,157 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 01:01:20,157 - simple_memory_calculator - INFO - Generating memory recommendations for black-forest-labs/FLUX.1-schnell with 16.0GB VRAM
+2025-05-30 01:01:20,157 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 01:01:20,158 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 01:01:20,158 - simple_memory_calculator - DEBUG - Model memory: 24.0GB, Inference memory: 36.0GB
+2025-05-30 01:01:20,158 - simple_memory_calculator - INFO - Getting memory requirements for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 01:01:20,158 - simple_memory_calculator - DEBUG - Using cached memory data for black-forest-labs/FLUX.1-schnell
+2025-05-30 01:01:20,158 - auto_diffusers - INFO - Starting code generation for model: black-forest-labs/FLUX.1-schnell
+2025-05-30 01:01:20,158 - auto_diffusers - DEBUG - Parameters: prompt='A cat holding a sign that says hello world...', size=(768, 1360), steps=4
+2025-05-30 01:01:20,158 - auto_diffusers - DEBUG - Manual specs: True, Memory analysis provided: True
+2025-05-30 01:01:20,158 - auto_diffusers - INFO - Using manual hardware specifications
+2025-05-30 01:01:20,158 - auto_diffusers - DEBUG - Manual specs: {'platform': 'Linux', 'architecture': 'manual_input', 'cpu_count': 8, 'python_version': '3.11', 'cuda_available': False, 'mps_available': False, 'torch_version': '2.0+', 'manual_input': True, 'ram_gb': 16, 'user_dtype': None, 'gpu_info': [{'name': 'RTX 5070 Ti', 'memory_mb': 16384}]}
+2025-05-30 01:01:20,158 - auto_diffusers - DEBUG - GPU detected with 16.0 GB VRAM
+2025-05-30 01:01:20,158 - auto_diffusers - INFO - Selected optimization profile: performance
+2025-05-30 01:01:20,158 - auto_diffusers - DEBUG - Creating generation prompt for Gemini API
+2025-05-30 01:01:20,158 - auto_diffusers - DEBUG - Prompt length: 7603 characters
+2025-05-30 01:01:20,158 - auto_diffusers - INFO - ================================================================================
+2025-05-30 01:01:20,158 - auto_diffusers - INFO - PROMPT SENT TO GEMINI API:
+2025-05-30 01:01:20,158 - auto_diffusers - INFO - ================================================================================
+2025-05-30 01:01:20,159 - auto_diffusers - INFO - 
+You are an expert in optimizing diffusers library code for different hardware configurations.
+
+NOTE: This system includes curated optimization knowledge from HuggingFace documentation.
+
+TASK: Generate optimized Python code for running a diffusion model with the following specifications:
+- Model: black-forest-labs/FLUX.1-schnell
+- Prompt: "A cat holding a sign that says hello world"
+- Image size: 768x1360
+- Inference steps: 4
+
+HARDWARE SPECIFICATIONS:
+- Platform: Linux (manual_input)
+- CPU Cores: 8
+- CUDA Available: False
+- MPS Available: False
+- Optimization Profile: performance
+- GPU: RTX 5070 Ti (16.0 GB VRAM)
+
+MEMORY ANALYSIS:
+- Model Memory Requirements: 36.0 GB (FP16 inference)
+- Model Weights Size: 24.0 GB (FP16)
+- Memory Recommendation: 🔄 Requires sequential CPU offloading
+- Recommended Precision: float16
+- Attention Slicing Recommended: True
+- VAE Slicing Recommended: True
+
+OPTIMIZATION KNOWLEDGE BASE:
+
+# DIFFUSERS OPTIMIZATION TECHNIQUES
+
+## Memory Optimization Techniques
+
+### 1. Model CPU Offloading
+Use `enable_model_cpu_offload()` to move models between GPU and CPU automatically:
+```python
+pipe.enable_model_cpu_offload()
+```
+- Saves significant VRAM by keeping only active models on GPU
+- Automatic management, no manual intervention needed
+- Compatible with all pipelines
+
+### 2. Sequential CPU Offloading  
+Use `enable_sequential_cpu_offload()` for more aggressive memory saving:
+```python
+pipe.enable_sequential_cpu_offload()
+```
+- More memory efficient than model offloading
+- Moves models to CPU after each forward pass
+- Best for very limited VRAM scenarios
+
+### 3. Attention Slicing
+Use `enable_attention_slicing()` to reduce memory during attention computation:
+```python
+pipe.enable_attention_slicing()
+# or specify slice size
+pipe.enable_attention_slicing("max")  # maximum slicing
+pipe.enable_attention_slicing(1)      # slice_size = 1
+```
+- Trades compute time for memory
+- Most effective for high-resolution images
+- Can be combined with other techniques
+
+### 4. VAE Slicing
+Use `enable_vae_slicing()` for large batch processing:
+```python
+pipe.enable_vae_slicing()
+```
+- Decodes images one at a time instead of all at once
+- Essential for batch sizes > 4
+- Minimal performance impact on single images
+
+### 5. VAE Tiling
+Use `enable_vae_tiling()` for high-resolution image generation:
+```python
+pipe.enable_vae_tiling()
+```
+- Enables 4K+ image generation on 8GB VRAM
+- Splits images into overlapping tiles
+- Automatically disabled for 512x512 or smaller images
+
+### 6. Memory Efficient Attention (xFormers)
+Use `enable_xformers_memory_efficient_attention()` if xFormers is installed:
+```python
+pipe.enable_xformers_memory_efficient_attention()
+```
+- Significantly reduces memory usage and improves speed
+- Requires xformers library installation
+- Compatible with most models
+
+## Performance Optimization Techniques
+
+### 1. Half Precision (FP16/BF16)
+Use lower precision for better memory and speed:
+```python
+# FP16 (widely supported)
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+
+# BF16 (better numerical stability, newer hardware)
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+```
+- FP16: Halves memory usage, widely supported
+- BF16: Better numerical stability, requires newer GPUs
+- Essential for most optimization scenarios
+
+### 2. Torch Compile (PyTorch 2.0+)
+Use `torch.compile()` for significant speed improvements:
+```python
+pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+# For some models, compile VAE too:
+pipe.vae.decode = torch.compile(pipe.vae.decode, mode="reduce-overhead", fullgraph=True)
+```
+- 5-50% speed improvement
+- Requires PyTorch 2.0+
+- First run is slower due to compilation
+
+### 3. Fast Schedulers
+Use faster schedulers for fewer steps:
+```python
+from diffusers import LMSDiscreteScheduler, UniPCMultistepScheduler
+
+# LMS Scheduler (good quality, fast)
+pipe.scheduler = LMSDiscreteScheduler.from_config(pipe.scheduler.config)
+
+# UniPC Scheduler (fastest)
+pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
+```
+
+## Hardware-Specific Optimizations
+
+### NVIDIA GPU Optimizations
+```python
+# Enable Tensor Cores
+torch.backends.cudnn.benchmark = True
+
+# Optimal data type for NVIDIA
+torch_dtype = torch.float16  # or torch.bfloat16 for RTX 30/40 series
+```
+
+### Apple Silicon (MPS) Optimizations
+```python
+# Use MPS device
+device = "mps" if torch.backends.mps.is_available() else "cpu"
+pipe = pipe.to(device)
+
+# Recommended dtype for Apple Silicon
+torch_dtype = torch.bfloat16  # Better than float16 on Apple Silicon
+
+# Attention slicing often helps on MPS
+pipe.enable_attention_slicing()
+```
+
+### CPU Optimizations
+```python
+# Use float32 for CPU
+torch_dtype = torch.float32
+
+# Enable optimized attention
+pipe.enable_attention_slicing()
+```
+
+## Model-Specific Guidelines
+
+### FLUX Models
+- Do NOT use guidance_scale parameter (not needed for FLUX)
+- Use 4-8 inference steps maximum
+- BF16 dtype recommended
+- Enable attention slicing for memory optimization
+
+### Stable Diffusion XL
+- Enable attention slicing for high resolutions
+- Use refiner model sparingly to save memory
+- Consider VAE tiling for >1024px images
+
+### Stable Diffusion 1.5/2.1
+- Very memory efficient base models
+- Can often run without optimizations on 8GB+ VRAM
+- Enable VAE slicing for batch processing
+
+## Memory Usage Estimation
+- FLUX.1: ~24GB for full precision, ~12GB for FP16
+- SDXL: ~7GB for FP16, ~14GB for FP32
+- SD 1.5: ~2GB for FP16, ~4GB for FP32
+
+## Optimization Combinations by VRAM
+
+### 24GB+ VRAM (High-end)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16)
+pipe = pipe.to("cuda")
+pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
+```
+
+### 12-24GB VRAM (Mid-range)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+pipe.enable_model_cpu_offload()
+pipe.enable_xformers_memory_efficient_attention()
+```
+
+### 8-12GB VRAM (Entry-level)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe.enable_sequential_cpu_offload()
+pipe.enable_attention_slicing()
+pipe.enable_vae_slicing()
+pipe.enable_xformers_memory_efficient_attention()
+```
+
+### <8GB VRAM (Low-end)
+```python
+pipe = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe.enable_sequential_cpu_offload()
+pipe.enable_attention_slicing("max")
+pipe.enable_vae_slicing()
+pipe.enable_vae_tiling()
+```
+
+
+IMPORTANT: For FLUX.1-schnell models, do NOT include guidance_scale parameter as it's not needed.
+
+Using the OPTIMIZATION KNOWLEDGE BASE above, generate Python code that:
+
+1. **Selects the best optimization techniques** for the specific hardware profile
+2. **Applies appropriate memory optimizations** based on available VRAM
+3. **Uses optimal data types** for the target hardware:
+   - User specified dtype (if provided): Use exactly as specified
+   - Apple Silicon (MPS): prefer torch.bfloat16
+   - NVIDIA GPUs: prefer torch.float16 or torch.bfloat16 
+   - CPU only: use torch.float32
+4. **Implements hardware-specific optimizations** (CUDA, MPS, CPU)
+5. **Follows model-specific guidelines** (e.g., FLUX guidance_scale handling)
+
+IMPORTANT GUIDELINES:
+- Reference the OPTIMIZATION KNOWLEDGE BASE to select appropriate techniques
+- Include all necessary imports
+- Add brief comments explaining optimization choices
+- Generate compact, production-ready code
+- Inline values where possible for concise code
+- Generate ONLY the Python code, no explanations before or after the code block
+
+2025-05-30 01:01:20,159 - auto_diffusers - INFO - ================================================================================
+2025-05-30 01:01:20,159 - auto_diffusers - INFO - Sending request to Gemini API
+2025-05-30 01:01:43,263 - auto_diffusers - INFO - Successfully received response from Gemini API (no tools used)
+2025-05-30 01:01:43,263 - auto_diffusers - DEBUG - Response length: 2591 characters