Update app.py

app.py

@@ -25,13 +25,7 @@ pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
     controlnet=controlnet,
     vae=vae,
     torch_dtype=precision,
-)
-
-pipe.enable_model_cpu_offload()
-pipe.to(device)
-
-## to move in the function
-controlnet_conditioning_scale = 0.5  # recommended for good generalization
+).to(device)
 
 # 📸 Edge detection function using OpenCV (Canny)
 @spaces.GPU
@@ -44,7 +38,7 @@ def apply_canny(image, low_threshold, high_threshold):
 
 # 🎨 Image generation function
 @spaces.GPU
-def generate_image(prompt, input_image, low_threshold, high_threshold, strength, guidance):
+def generate_image(prompt, input_image, low_threshold, high_threshold, strength, guidance, controlnet_conditioning_scale):
     # Apply edge detection
     edge_detected = apply_canny(input_image, low_threshold, high_threshold)
     
@@ -74,6 +68,7 @@ with gr.Blocks() as demo:
             
             strength = gr.Slider(0.1, 1.0, value=0.8, label="Denoising Strength")
             guidance = gr.Slider(1, 20, value=7.5, label="Guidance Scale (Creativity)")
+            controlnet_conditioning_scale = gr.Slider(0, 1, value=0.5, label="ControlNet Conditioning Scale")
             
             generate_button = gr.Button("Generate Styled Image")
 
@@ -84,7 +79,7 @@ with gr.Blocks() as demo:
     # 🔗 Button Action
     generate_button.click(
         fn=generate_image,
-        inputs=[prompt, input_image, low_threshold, high_threshold, strength, guidance],
+        inputs=[prompt, input_image, low_threshold, high_threshold, strength, guidance, controlnet_conditioning_scale],
         outputs=[edge_output, result_output]
     )