Revamp Gradio interface for 3D character generation, enhancing input options and output display while streamlining the image processing workflow.

app.py

@@ -207,85 +207,79 @@ _DESCRIPTION = '''
 '''
 
 # Create Gradio interface
-with gr.Blocks(title="CRM: 3D Character Generation from Single Image") as demo:
+with gr.Blocks() as demo:
+    gr.Markdown("# CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model")
     gr.Markdown(_DESCRIPTION)
-    
     with gr.Row():
         with gr.Column():
-            input_image = gr.Image(label="Input Image", type="pil")
-            background_choice = gr.Radio(
-                choices=["Remove Background", "Custom Background"],
-                value="Remove Background",
-                label="Background Option"
-            )
-            foreground_ratio = gr.Slider(
-                minimum=0.1,
-                maximum=1.0,
-                value=1.0,
-                step=0.1,
-                label="Foreground Ratio"
-            )
-            back_groud_color = gr.ColorPicker(
-                label="Background Color",
-                value="#FFFFFF"
-            )
-            seed = gr.Number(
-                label="Seed",
-                value=42,
-                precision=0
-            )
-            scale = gr.Slider(
-                minimum=1.0,
-                maximum=20.0,
-                value=7.5,
-                step=0.1,
-                label="Guidance Scale"
-            )
-            step = gr.Slider(
-                minimum=1,
-                maximum=100,
-                value=50,
-                step=1,
-                label="Steps"
+            with gr.Row():
+                image_input = gr.Image(
+                    label="Image input",
+                    image_mode="RGBA",
+                    sources="upload",
+                    type="pil",
+                )
+                processed_image = gr.Image(label="Processed Image", interactive=False, type="pil", image_mode="RGB")
+            with gr.Row():
+                with gr.Column():
+                    with gr.Row():
+                        background_choice = gr.Radio([
+                                "Alpha as mask",
+                                "Auto Remove background"
+                            ], value="Auto Remove background",
+                            label="background choice")
+                    back_groud_color = gr.ColorPicker(label="Background Color", value="#7F7F7F", interactive=False)
+                    foreground_ratio = gr.Slider(
+                        label="Foreground Ratio",
+                        minimum=0.5,
+                        maximum=1.0,
+                        value=1.0,
+                        step=0.05,
+                    )
+
+                with gr.Column():
+                    seed = gr.Number(value=1234, label="seed", precision=0)
+                    guidance_scale = gr.Number(value=5.5, minimum=3, maximum=10, label="guidance_scale")
+                    step = gr.Number(value=30, minimum=30, maximum=100, label="sample steps", precision=0)
+            text_button = gr.Button("Generate 3D shape")
+            gr.Examples(
+                examples=[os.path.join("examples", i) for i in os.listdir("examples")],
+                inputs=[image_input],
+                examples_per_page=20,
             )
-            generate_btn = gr.Button("Generate 3D Model")
-            
         with gr.Column():
-            processed_image = gr.Image(label="Processed Image", type="pil")
-            output_image = gr.Image(label="Generated Image", type="pil")
-            output_xyz = gr.Image(label="Generated XYZ", type="pil")
-            output_glb = gr.Model3D(label="Generated 3D Model")
-    
-    def process_and_generate(input_image, background_choice, foreground_ratio, back_groud_color, seed, scale, step):
-        # First check input
-        input_image = check_input_image(input_image)
-        # Then preprocess
-        processed = preprocess_image(input_image, background_choice, foreground_ratio, back_groud_color)
-        # Finally generate
-        output_img, output_xyz_img, glb_path = gen_image(processed, seed, scale, step)
-        return processed, output_img, output_xyz_img, glb_path
+            image_output = gr.Image(interactive=False, label="Output RGB image")
+            xyz_output = gr.Image(interactive=False, label="Output CCM image")
+            output_model = gr.Model3D(
+                label="Output GLB",
+                interactive=False,
+            )
+            gr.Markdown("Note: Ensure that the input image is correctly pre-processed into a grey background, otherwise the results will be unpredictable.")
+
+    inputs = [
+        processed_image,
+        seed,
+        guidance_scale,
+        step,
+    ]
+    outputs = [
+        image_output,
+        xyz_output,
+        output_model,
+    ]
 
-    # Connect the functions with a single API endpoint
-    generate_btn.click(
-        fn=process_and_generate,
-        inputs=[
-            input_image,
-            background_choice,
-            foreground_ratio,
-            back_groud_color,
-            seed,
-            scale,
-            step
-        ],
-        outputs=[
-            processed_image,
-            output_image,
-            output_xyz,
-            output_glb
-        ]
+    text_button.click(fn=check_input_image, inputs=[image_input]).success(
+        fn=preprocess_image,
+        inputs=[image_input, background_choice, foreground_ratio, back_groud_color],
+        outputs=[processed_image],
+    ).success(
+        fn=gen_image,
+        inputs=inputs,
+        outputs=outputs,
     )
 
-# For Hugging Face Spaces, use minimal configuration
-demo.queue().launch(
-    show_error=True  # Only keep error display for debugging
+# Launch the interface
+demo.queue(concurrency_count=1).launch(
+    show_error=True,
+    share=False
 )