Refactor Gradio interface to use a simpler structure with a single Interface instead of Blocks, enhancing clarity and usability while maintaining concurrency limits and error handling for image uploads.

app.py

@@ -206,86 +206,54 @@ _DESCRIPTION = '''
 * If you find the output unsatisfying, try using different seeds:)
 '''
 
-# Create Gradio interface
-with gr.Blocks(analytics_enabled=False) as demo:  # Disable analytics to reduce complexity
-    gr.Markdown("# CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model")
-    gr.Markdown(_DESCRIPTION)
-    with gr.Row():
-        with gr.Column():
-            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,
-            )
-        with gr.Column():
-            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.")
-
-    def generate(image, bg_choice, fg_ratio, bg_color, seed_val, guidance, steps):
-        if image is None:
-            raise gr.Error("No image uploaded!")
-        processed = preprocess_image(image, bg_choice, fg_ratio, bg_color)
-        return gen_image(processed, seed_val, guidance, steps)
+def generate(image, bg_choice, fg_ratio, bg_color, seed_val, guidance, steps):
+    if image is None:
+        raise gr.Error("No image uploaded!")
+    processed = preprocess_image(image, bg_choice, fg_ratio, bg_color)
+    return gen_image(processed, seed_val, guidance, steps)
 
-    # Use concurrency_limit on the event listener and remove api_name
-    text_button.click(
-        fn=generate,
-        inputs=[
-            image_input,
-            background_choice,
-            foreground_ratio,
-            back_groud_color,
-            seed,
-            guidance_scale,
-            step
-        ],
-        outputs=[
-            image_output,
-            xyz_output,
-            output_model
-        ],
-        concurrency_limit=1   # Set concurrency limit directly on the event listener
-    )
+# Create a simple Interface instead of Blocks
+demo = gr.Interface(
+    fn=generate,
+    inputs=[
+        gr.Image(
+            label="Image input",
+            image_mode="RGBA",
+            sources="upload",
+            type="pil",
+        ),
+        gr.Radio(
+            ["Alpha as mask", "Auto Remove background"],
+            value="Auto Remove background",
+            label="background choice"
+        ),
+        gr.Slider(
+            label="Foreground Ratio",
+            minimum=0.5,
+            maximum=1.0,
+            value=1.0,
+            step=0.05,
+        ),
+        gr.ColorPicker(label="Background Color", value="#7F7F7F", interactive=False),
+        gr.Number(value=1234, label="seed", precision=0),
+        gr.Number(value=5.5, minimum=3, maximum=10, label="guidance_scale"),
+        gr.Number(value=30, minimum=30, maximum=100, label="sample steps", precision=0)
+    ],
+    outputs=[
+        gr.Image(interactive=False, label="Output RGB image"),
+        gr.Image(interactive=False, label="Output CCM image"),
+        gr.Model3D(label="Output GLB", interactive=False)
+    ],
+    title="CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model",
+    description=_DESCRIPTION,
+    examples=[[os.path.join("examples", i)] for i in os.listdir("examples")],
+    concurrency_limit=1,
+    analytics_enabled=False
+)
 
-# Launch the interface with necessary parameters for Hugging Face Spaces
+# Launch with minimal parameters
 demo.launch(
-    server_name="0.0.0.0",  # Allow external access
-    server_port=7860,       # Use the standard Gradio port
-    show_error=True,
-    max_threads=1          # Control total number of workers
+    server_name="0.0.0.0",
+    server_port=7860,
+    show_error=True
 )