feat: add gradio ui

app.py

@@ -373,156 +373,157 @@ async def remove_image_background(image: UploadFile = File(...), token: str = De
         raise HTTPException(status_code=500, detail=str(e))
 
 
-@app.get("/")
-async def root_():
-    return JSONResponse(content={"message": "HI!"})
-
-# with gr.Blocks(delete_cache=(600, 600)) as demo:
-#     gr.Markdown("""
-#     ## Image to 3D Asset with [TRELLIS](https://trellis3d.github.io/)
-#     * Upload an image and click "Generate" to create a 3D asset. If the image has alpha channel, it be used as the mask. Otherwise, we use `rembg` to remove the background.
-#     * If you find the generated 3D asset satisfactory, click "Extract GLB" to extract the GLB file and download it.
+# @app.get("/")
+# async def root_():
+#     return JSONResponse(content={"message": "HI!"})
+
+with gr.Blocks(delete_cache=(600, 600)) as demo:
+    gr.Markdown("""
+    ## Image to 3D Asset with [TRELLIS](https://trellis3d.github.io/)
+    * Upload an image and click "Generate" to create a 3D asset. If the image has alpha channel, it be used as the mask. Otherwise, we use `rembg` to remove the background.
+    * If you find the generated 3D asset satisfactory, click "Extract GLB" to extract the GLB file and download it.
     
-#     ✨New: 1) Experimental multi-image support. 2) Gaussian file extraction.
-#     """)
+    ✨New: 1) Experimental multi-image support. 2) Gaussian file extraction.
+    """)
+    demo.load(verify_token)
     
-#     with gr.Row():
-#         with gr.Column():
-#             with gr.Tabs() as input_tabs:
-#                 with gr.Tab(label="Single Image", id=0) as single_image_input_tab:
-#                     image_prompt = gr.Image(label="Image Prompt", format="png", image_mode="RGBA", type="pil", height=300)
-#                 with gr.Tab(label="Multiple Images", id=1) as multiimage_input_tab:
-#                     multiimage_prompt = gr.Gallery(label="Image Prompt", format="png", type="pil", height=300, columns=3)
-#                     gr.Markdown("""
-#                         Input different views of the object in separate images. 
+    with gr.Row():
+        with gr.Column():
+            with gr.Tabs() as input_tabs:
+                with gr.Tab(label="Single Image", id=0) as single_image_input_tab:
+                    image_prompt = gr.Image(label="Image Prompt", format="png", image_mode="RGBA", type="pil", height=300)
+                with gr.Tab(label="Multiple Images", id=1) as multiimage_input_tab:
+                    multiimage_prompt = gr.Gallery(label="Image Prompt", format="png", type="pil", height=300, columns=3)
+                    gr.Markdown("""
+                        Input different views of the object in separate images. 
                         
-#                         *NOTE: this is an experimental algorithm without training a specialized model. It may not produce the best results for all images, especially those having different poses or inconsistent details.*
-#                     """)
+                        *NOTE: this is an experimental algorithm without training a specialized model. It may not produce the best results for all images, especially those having different poses or inconsistent details.*
+                    """)
             
-#             with gr.Accordion(label="Generation Settings", open=False):
-#                 seed = gr.Slider(0, MAX_SEED, label="Seed", value=0, step=1)
-#                 randomize_seed = gr.Checkbox(label="Randomize Seed", value=True)
-#                 gr.Markdown("Stage 1: Sparse Structure Generation")
-#                 with gr.Row():
-#                     ss_guidance_strength = gr.Slider(0.0, 10.0, label="Guidance Strength", value=7.5, step=0.1)
-#                     ss_sampling_steps = gr.Slider(1, 50, label="Sampling Steps", value=12, step=1)
-#                 gr.Markdown("Stage 2: Structured Latent Generation")
-#                 with gr.Row():
-#                     slat_guidance_strength = gr.Slider(0.0, 10.0, label="Guidance Strength", value=3.0, step=0.1)
-#                     slat_sampling_steps = gr.Slider(1, 50, label="Sampling Steps", value=12, step=1)
-#                 multiimage_algo = gr.Radio(["stochastic", "multidiffusion"], label="Multi-image Algorithm", value="stochastic")
-
-#             generate_btn = gr.Button("Generate")
+            with gr.Accordion(label="Generation Settings", open=False):
+                seed = gr.Slider(0, MAX_SEED, label="Seed", value=0, step=1)
+                randomize_seed = gr.Checkbox(label="Randomize Seed", value=True)
+                gr.Markdown("Stage 1: Sparse Structure Generation")
+                with gr.Row():
+                    ss_guidance_strength = gr.Slider(0.0, 10.0, label="Guidance Strength", value=7.5, step=0.1)
+                    ss_sampling_steps = gr.Slider(1, 50, label="Sampling Steps", value=12, step=1)
+                gr.Markdown("Stage 2: Structured Latent Generation")
+                with gr.Row():
+                    slat_guidance_strength = gr.Slider(0.0, 10.0, label="Guidance Strength", value=3.0, step=0.1)
+                    slat_sampling_steps = gr.Slider(1, 50, label="Sampling Steps", value=12, step=1)
+                multiimage_algo = gr.Radio(["stochastic", "multidiffusion"], label="Multi-image Algorithm", value="stochastic")
+
+            generate_btn = gr.Button("Generate")
             
-#             with gr.Accordion(label="GLB Extraction Settings", open=False):
-#                 mesh_simplify = gr.Slider(0.9, 0.98, label="Simplify", value=0.95, step=0.01)
-#                 texture_size = gr.Slider(512, 2048, label="Texture Size", value=1024, step=512)
+            with gr.Accordion(label="GLB Extraction Settings", open=False):
+                mesh_simplify = gr.Slider(0.9, 0.98, label="Simplify", value=0.95, step=0.01)
+                texture_size = gr.Slider(512, 2048, label="Texture Size", value=1024, step=512)
             
-#             with gr.Row():
-#                 extract_glb_btn = gr.Button("Extract GLB", interactive=False)
-#                 extract_gs_btn = gr.Button("Extract Gaussian", interactive=False)
-#             gr.Markdown("""
-#                         *NOTE: Gaussian file can be very large (~50MB), it will take a while to display and download.*
-#                         """)
-
-#         with gr.Column():
-#             video_output = gr.Video(label="Generated 3D Asset", autoplay=True, loop=True, height=300)
-#             model_output = LitModel3D(label="Extracted GLB/Gaussian", exposure=10.0, height=300)
+            with gr.Row():
+                extract_glb_btn = gr.Button("Extract GLB", interactive=False)
+                extract_gs_btn = gr.Button("Extract Gaussian", interactive=False)
+            gr.Markdown("""
+                        *NOTE: Gaussian file can be very large (~50MB), it will take a while to display and download.*
+                        """)
+
+        with gr.Column():
+            video_output = gr.Video(label="Generated 3D Asset", autoplay=True, loop=True, height=300)
+            model_output = LitModel3D(label="Extracted GLB/Gaussian", exposure=10.0, height=300)
             
-#             with gr.Row():
-#                 download_glb = gr.DownloadButton(label="Download GLB", interactive=False)
-#                 download_gs = gr.DownloadButton(label="Download Gaussian", interactive=False)  
+            with gr.Row():
+                download_glb = gr.DownloadButton(label="Download GLB", interactive=False)
+                download_gs = gr.DownloadButton(label="Download Gaussian", interactive=False)  
     
-#     is_multiimage = gr.State(False)
-#     output_buf = gr.State()
-
-#     # Example images at the bottom of the page
-#     with gr.Row() as single_image_example:
-#         examples = gr.Examples(
-#             examples=[
-#                 f'assets/example_image/{image}'
-#                 for image in os.listdir("assets/example_image")
-#             ],
-#             inputs=[image_prompt],
-#             fn=preprocess_image,
-#             outputs=[image_prompt],
-#             run_on_click=True,
-#             examples_per_page=64,
-#         )
-#     with gr.Row(visible=False) as multiimage_example:
-#         examples_multi = gr.Examples(
-#             examples=prepare_multi_example(),
-#             inputs=[image_prompt],
-#             fn=split_image,
-#             outputs=[multiimage_prompt],
-#             run_on_click=True,
-#             examples_per_page=8,
-#         )
-
-#     # Handlers
-#     demo.load(start_session)
-#     demo.unload(end_session)
+    is_multiimage = gr.State(False)
+    output_buf = gr.State()
+
+    # Example images at the bottom of the page
+    with gr.Row() as single_image_example:
+        examples = gr.Examples(
+            examples=[
+                f'assets/example_image/{image}'
+                for image in os.listdir("assets/example_image")
+            ],
+            inputs=[image_prompt],
+            fn=preprocess_image,
+            outputs=[image_prompt],
+            run_on_click=True,
+            examples_per_page=64,
+        )
+    with gr.Row(visible=False) as multiimage_example:
+        examples_multi = gr.Examples(
+            examples=prepare_multi_example(),
+            inputs=[image_prompt],
+            fn=split_image,
+            outputs=[multiimage_prompt],
+            run_on_click=True,
+            examples_per_page=8,
+        )
+
+    # Handlers
+    demo.load(start_session)
+    demo.unload(end_session)
     
-#     single_image_input_tab.select(
-#         lambda: tuple([False, gr.Row.update(visible=True), gr.Row.update(visible=False)]),
-#         outputs=[is_multiimage, single_image_example, multiimage_example]
-#     )
-#     multiimage_input_tab.select(
-#         lambda: tuple([True, gr.Row.update(visible=False), gr.Row.update(visible=True)]),
-#         outputs=[is_multiimage, single_image_example, multiimage_example]
-#     )
+    single_image_input_tab.select(
+        lambda: tuple([False, gr.Row.update(visible=True), gr.Row.update(visible=False)]),
+        outputs=[is_multiimage, single_image_example, multiimage_example]
+    )
+    multiimage_input_tab.select(
+        lambda: tuple([True, gr.Row.update(visible=False), gr.Row.update(visible=True)]),
+        outputs=[is_multiimage, single_image_example, multiimage_example]
+    )
     
-#     image_prompt.upload(
-#         preprocess_image,
-#         inputs=[image_prompt],
-#         outputs=[image_prompt],
-#     )
-#     multiimage_prompt.upload(
-#         preprocess_images,
-#         inputs=[multiimage_prompt],
-#         outputs=[multiimage_prompt],
-#     )
-
-#     generate_btn.click(
-#         get_seed,
-#         inputs=[randomize_seed, seed],
-#         outputs=[seed],
-#     ).then(
-#         image_to_3d,
-#         inputs=[image_prompt, multiimage_prompt, is_multiimage, seed, ss_guidance_strength, ss_sampling_steps, slat_guidance_strength, slat_sampling_steps, multiimage_algo],
-#         outputs=[output_buf, video_output],
-#     ).then(
-#         lambda: tuple([gr.Button(interactive=True), gr.Button(interactive=True)]),
-#         outputs=[extract_glb_btn, extract_gs_btn],
-#     )
-
-#     video_output.clear(
-#         lambda: tuple([gr.Button(interactive=False), gr.Button(interactive=False)]),
-#         outputs=[extract_glb_btn, extract_gs_btn],
-#     )
-
-#     extract_glb_btn.click(
-#         extract_glb,
-#         inputs=[output_buf, mesh_simplify, texture_size],
-#         outputs=[model_output, download_glb],
-#     ).then(
-#         lambda: gr.Button(interactive=True),
-#         outputs=[download_glb],
-#     )
+    image_prompt.upload(
+        preprocess_image,
+        inputs=[image_prompt],
+        outputs=[image_prompt],
+    )
+    multiimage_prompt.upload(
+        preprocess_images,
+        inputs=[multiimage_prompt],
+        outputs=[multiimage_prompt],
+    )
+
+    generate_btn.click(
+        get_seed,
+        inputs=[randomize_seed, seed],
+        outputs=[seed],
+    ).then(
+        image_to_3d,
+        inputs=[image_prompt, multiimage_prompt, is_multiimage, seed, ss_guidance_strength, ss_sampling_steps, slat_guidance_strength, slat_sampling_steps, multiimage_algo],
+        outputs=[output_buf, video_output],
+    ).then(
+        lambda: tuple([gr.Button(interactive=True), gr.Button(interactive=True)]),
+        outputs=[extract_glb_btn, extract_gs_btn],
+    )
+
+    video_output.clear(
+        lambda: tuple([gr.Button(interactive=False), gr.Button(interactive=False)]),
+        outputs=[extract_glb_btn, extract_gs_btn],
+    )
+
+    extract_glb_btn.click(
+        extract_glb,
+        inputs=[output_buf, mesh_simplify, texture_size],
+        outputs=[model_output, download_glb],
+    ).then(
+        lambda: gr.Button(interactive=True),
+        outputs=[download_glb],
+    )
     
-#     extract_gs_btn.click(
-#         extract_gaussian,
-#         inputs=[output_buf],
-#         outputs=[model_output, download_gs],
-#     ).then(
-#         lambda: gr.Button(interactive=True),
-#         outputs=[download_gs],
-#     )
-
-#     model_output.clear(
-#         lambda: gr.Button(interactive=False),
-#         outputs=[download_glb],
-#     )
+    extract_gs_btn.click(
+        extract_gaussian,
+        inputs=[output_buf],
+        outputs=[model_output, download_gs],
+    ).then(
+        lambda: gr.Button(interactive=True),
+        outputs=[download_gs],
+    )
+
+    model_output.clear(
+        lambda: gr.Button(interactive=False),
+        outputs=[download_glb],
+    )
     
 
 # Launch the Gradio app
@@ -535,6 +536,6 @@ if __name__ == "__main__":
     pipeline.cuda()
     
     print("STARTING SERVER ...")
-    # app = mount_gradio_app(app, demo, path="/")
+    app = mount_gradio_app(app, demo, path="/")
     uvicorn.run(app, host="0.0.0.0", port=7860)
     print("SERVER STARTED!!!")