Spaces:
Paused
Paused
File size: 3,607 Bytes
fdd3761 8124057 38d816c c1ad0ba 38d816c 4e7c237 38d816c d3a3bf1 fdd3761 d3a3bf1 fdd3761 4e7c237 d3a3bf1 4e7c237 d3a3bf1 4e7c237 d3a3bf1 8124057 d3a3bf1 fdd3761 d3a3bf1 4e7c237 d3a3bf1 4e7c237 d3a3bf1 fdd3761 8124057 d3a3bf1 38d816c d3a3bf1 8124057 fdd3761 8124057 d3a3bf1 38d816c 8124057 38d816c fdd3761 38d816c 8124057 38d816c fdd3761 38d816c 4e7c237 38d816c 8124057 d3a3bf1 38d816c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 |
# app.py
import gradio as gr
from PIL import Image
import base64
import requests
import os
from io import BytesIO
from utils.planner import extract_scene_plan # 🧠 Brain Layer
# 🔐 Hugging Face keys
HF_API_KEY = os.getenv("HF_API_KEY")
SDXL_MODEL_ID = "fal-ai/fast-sdxl/image-to-image" # ✅ Correct model for image-to-image
SDXL_API_URL = f"https://api-inference.huggingface.co/models/{SDXL_MODEL_ID}"
HEADERS = {"Authorization": f"Bearer {HF_API_KEY}"}
# 🚀 Image generation (img2img)
def process_image(prompt, image, num_variations):
try:
print("🧠 Prompt received:", prompt)
# Step 1: Brain Layer
reasoning_json = extract_scene_plan(prompt)
print("🧠 Scene plan extracted:", reasoning_json)
# Step 2: Encode input image
buffered = BytesIO()
image.save(buffered, format="JPEG")
img_bytes = buffered.getvalue()
encoded_image = base64.b64encode(img_bytes).decode("utf-8")
# Step 3: Send image + prompt to HF API
outputs = []
for i in range(num_variations):
payload = {
"image": encoded_image,
"prompt": prompt,
"negative_prompt": "blurry, deformed, cropped",
"num_inference_steps": 25,
"guidance_scale": 7.5
}
print(f"📤 Sending request to HF (variation {i+1})")
response = requests.post(SDXL_API_URL, headers=HEADERS, json=payload)
if response.status_code == 200:
try:
result_json = response.json()
if "images" in result_json:
base64_img = result_json["images"][0]
result_image = Image.open(BytesIO(base64.b64decode(base64_img)))
outputs.append(result_image)
print(f"✅ Decoded image variation {i+1} successfully")
else:
print(f"⚠️ No 'images' key found in response")
outputs.append("❌ No image in response.")
except Exception as decode_err:
print("❌ Image decode error:", decode_err)
outputs.append("❌ Failed to decode image.")
else:
print(f"❌ HF API error: {response.status_code} - {response.text}")
outputs.append(f"Error {response.status_code}: {response.text}")
return outputs, reasoning_json
except Exception as e:
print("❌ General Exception in process_image:", e)
return ["Processing error occurred"], {"error": str(e)}
# 🎨 Gradio UI
with gr.Blocks() as demo:
gr.Markdown("# 🧠 NewCrux AI Demo: Image-to-Image using Fast SDXL + Brain Layer")
with gr.Row():
with gr.Column():
prompt_input = gr.Textbox(label="Enter Prompt")
image_input = gr.Image(type="pil", label="Upload Product Image")
variation_slider = gr.Slider(1, 4, step=1, value=1, label="Number of Variations")
generate_btn = gr.Button("Generate")
with gr.Column():
output_gallery = gr.Gallery(
label="Generated Image Variations",
columns=2,
rows=2,
height="auto"
)
json_output = gr.JSON(label="Brain Layer Reasoning (Scene Plan)")
generate_btn.click(
fn=process_image,
inputs=[prompt_input, image_input, variation_slider],
outputs=[output_gallery, json_output]
)
demo.launch(share=True)
|