de

app.py

@@ -141,7 +141,7 @@ def outpaint_image(image):
   return image
 
 @spaces.GPU
-def predict_image(cond_image, prompt, negative_prompt):
+def predict_image(cond_image, prompt, negative_prompt, controlnet_conditioning_scale):
   print("predict position map")
   global pipe
   generator = torch.Generator()
@@ -157,7 +157,7 @@ def predict_image(cond_image, prompt, negative_prompt):
       num_inference_steps=20,
       generator=generator,
       guess_mode = True,
-      controlnet_conditioning_scale = 0.6,
+      controlnet_conditioning_scale = controlnet_conditioning_scale,
   ).images[0]
   
   return image
@@ -175,6 +175,7 @@ with gr.Blocks() as demo:
         img2 = gr.Image(type="pil", label="map Image", height=300)
       prompt = gr.Textbox("position map, 1girl, white background", label="Prompt")
       negative_prompt = gr.Textbox("lowres, bad anatomy, bad hands, bad feet, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry", label="Negative Prompt")
+      controlnet_conditioning_scale = gr.Slider(label="ControlNet conditioning scale", minimum=0.1, maximum=2.0, value=0.6, step=0.05)
       predict_map_btn = gr.Button("Predict Position Map")
       visualize_3d_btn = gr.Button("Generate 3D Point Cloud")
     with gr.Column():
@@ -188,7 +189,7 @@ with gr.Blocks() as demo:
       )
 
   img1.input(outpaint_image, inputs=img1, outputs=img1)
-  predict_map_btn.click(predict_image, inputs=[img1, prompt, negative_prompt], outputs=img2)
+  predict_map_btn.click(predict_image, inputs=[img1, prompt, negative_prompt, controlnet_conditioning_scale], outputs=img2)
   visualize_3d_btn.click(visualize_3d, inputs=[img2, img1], outputs=reconstruction_output)
 
 demo.launch()