Update app.py

app.py

@@ -1,65 +1,86 @@
 import gradio as gr
 import torch
-import numpy as np
-import cv2
+from diffusers import StableDiffusionPipeline
 from PIL import Image
-from diffusers import (
-    StableDiffusionControlNetPipeline,
-    ControlNetModel,
-    UniPCMultistepScheduler
-)
-
-# Load ControlNet model (Canny)
-controlnet = ControlNetModel.from_pretrained(
-    "lllyasviel/sd-controlnet-canny", torch_dtype=torch.float32
-)
-
-# Load Stable Diffusion pipeline with ControlNet
-pipe = StableDiffusionControlNetPipeline.from_pretrained(
-    "runwayml/stable-diffusion-v1-5",
-    controlnet=controlnet,
-    torch_dtype=torch.float32
-)
-
-# Set the scheduler
-pipe.scheduler = UniPCMultistepScheduler.from_config(pipe.scheduler.config)
-
-# Move the pipeline to the appropriate device
-pipe.to("cuda" if torch.cuda.is_available() else "cpu")
-
-def process_and_generate(image, prompt, num_inference_steps, guidance_scale):
-    # Convert PIL image to numpy array
-    image = np.array(image)
-
-    # Apply Canny edge detection
-    image = cv2.Canny(image, 100, 200)
-    image = image[:, :, None]
-    image = np.concatenate([image, image, image], axis=2)
-    canny_image = Image.fromarray(image)
-
-    # Generate image using the pipeline
-    result = pipe(
-        prompt=prompt,
-        image=canny_image,
-        num_inference_steps=num_inference_steps,
-        guidance_scale=guidance_scale,
+import time
+import traceback
+from typing import Optional
+
+# ---- Configuration ----
+model_id: str = "runwayml/stable-diffusion-v1-5"
+device: str = "cpu"  # force CPU usage for compatibility
+
+# ---- Load Model ----
+image_generator_pipe: Optional[StableDiffusionPipeline] = None
+
+try:
+    print(f"Loading Stable Diffusion pipeline ({model_id}) on CPU...")
+    pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float32)
+    image_generator_pipe = pipe.to(device)
+    print("Stable Diffusion pipeline loaded successfully.")
+except Exception as e:
+    print(f"Failed to load Stable Diffusion model: {e}")
+    traceback.print_exc()
+
+# ---- Core Image Generation Function ----
+def generate_image_sd(prompt: str, negative_prompt: str, guidance_scale: float, num_inference_steps: int) -> Image.Image:
+    if not image_generator_pipe:
+        raise gr.Error("Stable Diffusion pipeline failed to load. Image generation unavailable.")
+
+    if not prompt.strip():
+        raise gr.Error("Prompt cannot be empty.")
+
+    print(f"Generating image with prompt: {prompt[:100]}...")
+    print(f"Negative prompt: {negative_prompt}")
+    print(f"Guidance scale: {guidance_scale}, Steps: {num_inference_steps}")
+
+    start_time = time.time()
+
+    try:
+        with torch.no_grad():
+            output = image_generator_pipe(
+                prompt=prompt,
+                negative_prompt=negative_prompt,
+                guidance_scale=guidance_scale,
+                num_inference_steps=num_inference_steps
+            )
+            image = output.images[0] if output.images else None
+
+        if not image:
+            raise RuntimeError("No image was returned from the generation pipeline.")
+
+        end_time = time.time()
+        print(f"Image generated in {end_time - start_time:.2f} seconds.")
+        return image
+
+    except Exception as e:
+        print(f"Error generating image: {e}")
+        traceback.print_exc()
+        raise gr.Error(f"Image generation failed: {e}")
+
+# ---- Gradio UI ----
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# Stable Diffusion Image Generator (CPU Mode)")
+
+    with gr.Row():
+        with gr.Column(scale=1):
+            prompt = gr.Textbox(label="Prompt", placeholder="A beautiful futuristic city skyline at night")
+            neg_prompt = gr.Textbox(label="Negative Prompt", placeholder="blurry, distorted, watermark")
+            guidance = gr.Slider(1.0, 15.0, value=7.5, step=0.5, label="Guidance Scale")
+            steps = gr.Slider(10, 50, value=25, step=1, label="Inference Steps")
+            generate_btn = gr.Button("Generate Image")
+
+        with gr.Column(scale=1):
+            output_image = gr.Image(label="Generated Image", type="pil")
+
+    generate_btn.click(
+        fn=generate_image_sd,
+        inputs=[prompt, neg_prompt, guidance, steps],
+        outputs=output_image
     )
 
-    return result.images[0]
-
-# Define the Gradio interface
-iface = gr.Interface(
-    fn=process_and_generate,
-    inputs=[
-        gr.Image(type="pil", label="Input Image"),
-        gr.Textbox(label="Prompt"),
-        gr.Slider(1, 100, value=50, step=1, label="Number of Inference Steps"),
-        gr.Slider(0.1, 10.0, value=7.5, step=0.1, label="Guidance Scale"),
-    ],
-    outputs=gr.Image(type="pil", label="Generated Image"),
-    title="🧠 Stable Diffusion with ControlNet (Canny)",
-    description="Upload an image and enter a prompt. The system uses Canny edge detection to guide Stable Diffusion generation.",
-)
-
-# Launch the app
-iface.launch()
+# ---- Launch ----
+if __name__ == "__main__":
+    if not image_generator_pipe:
+        print("WARNING: Image generator pipeline is not available. UI will launch, but generation will fail.")
+    demo.launch(server_name="0.0.0.0", server_port=7860)