first lora

README.md

@@ -1,13 +0,0 @@
----
-title: FLUX.1-dev + Captioner
-emoji: 🐨
-colorFrom: blue
-colorTo: indigo
-sdk: gradio
-sdk_version: 4.37.2
-app_file: app.py
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

flux_lora.py → app.py

@@ -1,109 +1,109 @@
-import spaces
-import argparse
-import os
-import time
-from os import path
-from safetensors.torch import load_file
-from huggingface_hub import hf_hub_download
-
-cache_path = path.join(path.dirname(path.abspath(__file__)), "models")
-os.environ["TRANSFORMERS_CACHE"] = cache_path
-os.environ["HF_HUB_CACHE"] = cache_path
-os.environ["HF_HOME"] = cache_path
-
-import gradio as gr
-import torch
-from diffusers import FluxPipeline
-
-torch.backends.cuda.matmul.allow_tf32 = True
-
-class timer:
-    def __init__(self, method_name="timed process"):
-        self.method = method_name
-    def __enter__(self):
-        self.start = time.time()
-        print(f"{self.method} starts")
-    def __exit__(self, exc_type, exc_val, exc_tb):
-        end = time.time()
-        print(f"{self.method} took {str(round(end - self.start, 2))}s")
-
-if not path.exists(cache_path):
-    os.makedirs(cache_path, exist_ok=True)
-
-pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
-pipe.load_lora_weights(hf_hub_download("ByteDance/Hyper-SD", "Hyper-FLUX.1-dev-8steps-lora.safetensors"))
-pipe.fuse_lora(lora_scale=0.125)
-pipe.to(device="cuda", dtype=torch.bfloat16)
-
-with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown(
-        """
-        <div style="text-align: center; max-width: 650px; margin: 0 auto;">
-            <h1 style="font-size: 2.5rem; font-weight: 700; margin-bottom: 1rem; display: contents;">Hyper-FLUX-8steps-LoRA</h1>
-            <p style="font-size: 1rem; margin-bottom: 1.5rem;">AutoML team from ByteDance</p>
-        </div>
-        """
-    )
-
-    with gr.Row():
-        with gr.Column(scale=3):
-            with gr.Group():
-                prompt = gr.Textbox(
-                    label="Your Image Description",
-                    placeholder="E.g., A serene landscape with mountains and a lake at sunset",
-                    lines=3
-                )
-                
-                with gr.Accordion("Advanced Settings", open=False):
-                    with gr.Group():
-                        with gr.Row():
-                            height = gr.Slider(label="Height", minimum=256, maximum=1152, step=64, value=1024)
-                            width = gr.Slider(label="Width", minimum=256, maximum=1152, step=64, value=1024)
-                        
-                        with gr.Row():
-                            steps = gr.Slider(label="Inference Steps", minimum=6, maximum=25, step=1, value=8)
-                            scales = gr.Slider(label="Guidance Scale", minimum=0.0, maximum=5.0, step=0.1, value=3.5)
-                        
-                        seed = gr.Number(label="Seed (for reproducibility)", value=3413, precision=0)
-                
-                generate_btn = gr.Button("Generate Image", variant="primary", scale=1)
-
-        with gr.Column(scale=4):
-            output = gr.Image(label="Your Generated Image")
-    
-    gr.Markdown(
-        """
-        <div style="max-width: 650px; margin: 2rem auto; padding: 1rem; border-radius: 10px; background-color: #f0f0f0;">
-            <h2 style="font-size: 1.5rem; margin-bottom: 1rem;">How to Use</h2>
-            <ol style="padding-left: 1.5rem;">
-                <li>Enter a detailed description of the image you want to create.</li>
-                <li>Adjust advanced settings if desired (tap to expand).</li>
-                <li>Tap "Generate Image" and wait for your creation!</li>
-            </ol>
-            <p style="margin-top: 1rem; font-style: italic;">Tip: Be specific in your description for best results!</p>
-        </div>
-        """
-    )
-
-    @spaces.GPU
-    def process_image(height, width, steps, scales, prompt, seed):
-        global pipe
-        with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16), timer("inference"):
-            return pipe(
-                prompt=[prompt],
-                generator=torch.Generator().manual_seed(int(seed)),
-                num_inference_steps=int(steps),
-                guidance_scale=float(scales),
-                height=int(height),
-                width=int(width),
-                max_sequence_length=256
-            ).images[0]
-
-    generate_btn.click(
-        process_image,
-        inputs=[height, width, steps, scales, prompt, seed],
-        outputs=output
-    )
-
-if __name__ == "__main__":
+import spaces
+import argparse
+import os
+import time
+from os import path
+from safetensors.torch import load_file
+from huggingface_hub import hf_hub_download
+
+cache_path = path.join(path.dirname(path.abspath(__file__)), "models")
+os.environ["TRANSFORMERS_CACHE"] = cache_path
+os.environ["HF_HUB_CACHE"] = cache_path
+os.environ["HF_HOME"] = cache_path
+
+import gradio as gr
+import torch
+from diffusers import FluxPipeline
+
+torch.backends.cuda.matmul.allow_tf32 = True
+
+class timer:
+    def __init__(self, method_name="timed process"):
+        self.method = method_name
+    def __enter__(self):
+        self.start = time.time()
+        print(f"{self.method} starts")
+    def __exit__(self, exc_type, exc_val, exc_tb):
+        end = time.time()
+        print(f"{self.method} took {str(round(end - self.start, 2))}s")
+
+if not path.exists(cache_path):
+    os.makedirs(cache_path, exist_ok=True)
+
+pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
+pipe.load_lora_weights(hf_hub_download("gokaygokay/Flux-Game-Assets-LoRA-v2", "game_asst.safetensors"))
+pipe.fuse_lora(lora_scale=1)
+pipe.to(device="cuda", dtype=torch.bfloat16)
+
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown(
+        """
+        <div style="text-align: center; max-width: 650px; margin: 0 auto;">
+            <h1 style="font-size: 2.5rem; font-weight: 700; margin-bottom: 1rem; display: contents;">Hyper-FLUX-8steps-LoRA</h1>
+            <p style="font-size: 1rem; margin-bottom: 1.5rem;">AutoML team from ByteDance</p>
+        </div>
+        """
+    )
+
+    with gr.Row():
+        with gr.Column(scale=3):
+            with gr.Group():
+                prompt = gr.Textbox(
+                    label="Your Image Description",
+                    placeholder="E.g., A serene landscape with mountains and a lake at sunset",
+                    lines=3
+                )
+                
+                with gr.Accordion("Advanced Settings", open=False):
+                    with gr.Group():
+                        with gr.Row():
+                            height = gr.Slider(label="Height", minimum=256, maximum=1152, step=64, value=1024)
+                            width = gr.Slider(label="Width", minimum=256, maximum=1152, step=64, value=1024)
+                        
+                        with gr.Row():
+                            steps = gr.Slider(label="Inference Steps", minimum=10, maximum=50, step=1, value=28)
+                            scales = gr.Slider(label="Guidance Scale", minimum=0.0, maximum=5.0, step=0.1, value=3.5)
+                        
+                        seed = gr.Number(label="Seed (for reproducibility)", value=3413, precision=0)
+                
+                generate_btn = gr.Button("Generate Image", variant="primary", scale=1)
+
+        with gr.Column(scale=4):
+            output = gr.Image(label="Your Generated Image")
+    
+    gr.Markdown(
+        """
+        <div style="max-width: 650px; margin: 2rem auto; padding: 1rem; border-radius: 10px; background-color: #f0f0f0;">
+            <h2 style="font-size: 1.5rem; margin-bottom: 1rem;">How to Use</h2>
+            <ol style="padding-left: 1.5rem;">
+                <li>Enter a detailed description of the image you want to create.</li>
+                <li>Adjust advanced settings if desired (tap to expand).</li>
+                <li>Tap "Generate Image" and wait for your creation!</li>
+            </ol>
+            <p style="margin-top: 1rem; font-style: italic;">Tip: Be specific in your description for best results!</p>
+        </div>
+        """
+    )
+
+    @spaces.GPU
+    def process_image(height, width, steps, scales, prompt, seed):
+        global pipe
+        with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16), timer("inference"):
+            return pipe(
+                prompt=[prompt],
+                generator=torch.Generator().manual_seed(int(seed)),
+                num_inference_steps=int(steps),
+                guidance_scale=float(scales),
+                height=int(height),
+                width=int(width),
+                max_sequence_length=256
+            ).images[0]
+
+    generate_btn.click(
+        process_image,
+        inputs=[height, width, steps, scales, prompt, seed],
+        outputs=output
+    )
+
+if __name__ == "__main__":
     demo.launch()

requirements.txt

@@ -1,19 +1,23 @@
-torch>=2.1.2
-torchvision>=0.16.2
-einops>=0.7.0
-jaxtyping>=0.2.31
-omegaconf>=2.3.0
-transformers>=4.43.3
-slangtorch>=1.2.2
-open_clip_torch>=2.24.0
-trimesh>=4.4.1
-numpy>=1.26.4
-huggingface-hub>=0.23.4
-rembg[gpu]>=2.0.57
-gradio-litmodel3d>=0.0.1
+torch==2.1.0
+torchvision==0.16.0
+torchaudio==2.1.0
+pytorch-lightning==2.1.2
+einops
+omegaconf
+deepspeed
+torchmetrics
+webdataset
 accelerate
-diffusers>=0.30.0
-invisible_watermark
-xformers
-sentencepiece
-peft
+tensorboard
+PyMCubes
+trimesh
+rembg
+transformers==4.34.1
+diffusers==0.19.3
+bitsandbytes
+imageio[ffmpeg]
+xatlas
+plyfile
+xformers==0.0.22.post7
+git+https://github.com/NVlabs/nvdiffrast/
+huggingface-hub