Update app.py

app.py

@@ -31,30 +31,7 @@ def end_session(req: gr.Request):
     shutil.rmtree(user_dir)
 
 
-def preprocess_image(image: Image.Image) -> Image.Image:
-    """
-    Preprocess the input image.
-
-    Args:
-        image (Image.Image): The input image.
-
-    Returns:
-        Image.Image: The preprocessed image.
-    """
-    processed_image = pipeline.preprocess_image(image)
-    return processed_image
-
-
 def preprocess_images(images: List[Tuple[Image.Image, str]]) -> List[Image.Image]:
-    """
-    Preprocess a list of input images.
-    
-    Args:
-        images (List[Tuple[Image.Image, str]]): The input images.
-        
-    Returns:
-        List[Image.Image]: The preprocessed images.
-    """
     images = [image[0] for image in images]
     processed_images = [pipeline.preprocess_image(image) for image in images]
     return processed_images
@@ -101,15 +78,11 @@ def unpack_state(state: dict) -> Tuple[Gaussian, edict, str]:
 
 
 def get_seed(randomize_seed: bool, seed: int) -> int:
-    """
-    Get the random seed.
-    """
     return np.random.randint(0, MAX_SEED) if randomize_seed else seed
 
 
 @spaces.GPU
 def image_to_3d(
-    image: Image.Image,
     multiimages: List[Tuple[Image.Image, str]],
     is_multiimage: bool,
     seed: int,
@@ -120,24 +93,6 @@ def image_to_3d(
     multiimage_algo: Literal["multidiffusion", "stochastic"],
     req: gr.Request,
 ) -> Tuple[dict, str]:
-    """
-    Convert an image to a 3D model.
-
-    Args:
-        image (Image.Image): The input image.
-        multiimages (List[Tuple[Image.Image, str]]): The input images in multi-image mode.
-        is_multiimage (bool): Whether is in multi-image mode.
-        seed (int): The random seed.
-        ss_guidance_strength (float): The guidance strength for sparse structure generation.
-        ss_sampling_steps (int): The number of sampling steps for sparse structure generation.
-        slat_guidance_strength (float): The guidance strength for structured latent generation.
-        slat_sampling_steps (int): The number of sampling steps for structured latent generation.
-        multiimage_algo (Literal["multidiffusion", "stochastic"]): The algorithm for multi-image generation.
-
-    Returns:
-        dict: The information of the generated 3D model.
-        str: The path to the video of the 3D model.
-    """
     user_dir = os.path.join(TMP_DIR, str(req.session_hash))
     if not is_multiimage:
         outputs = pipeline.run(
@@ -187,17 +142,6 @@ def extract_glb(
     texture_size: int,
     req: gr.Request,
 ) -> Tuple[str, str]:
-    """
-    Extract a GLB file from the 3D model.
-
-    Args:
-        state (dict): The state of the generated 3D model.
-        mesh_simplify (float): The mesh simplification factor.
-        texture_size (int): The texture resolution.
-
-    Returns:
-        str: The path to the extracted GLB file.
-    """
     user_dir = os.path.join(TMP_DIR, str(req.session_hash))
     gs, mesh = unpack_state(state)
     glb = postprocessing_utils.to_glb(gs, mesh, simplify=mesh_simplify, texture_size=texture_size, verbose=False)
@@ -209,15 +153,6 @@ def extract_glb(
 
 @spaces.GPU
 def extract_gaussian(state: dict, req: gr.Request) -> Tuple[str, str]:
-    """
-    Extract a Gaussian file from the 3D model.
-
-    Args:
-        state (dict): The state of the generated 3D model.
-
-    Returns:
-        str: The path to the extracted Gaussian file.
-    """
     user_dir = os.path.join(TMP_DIR, str(req.session_hash))
     gs, _ = unpack_state(state)
     gaussian_path = os.path.join(user_dir, 'sample.ply')
@@ -239,44 +174,24 @@ def prepare_multi_example() -> List[Image.Image]:
         images.append(Image.fromarray(np.concatenate(_images, axis=1)))
     return images
 
-
-def split_image(image: Image.Image) -> List[Image.Image]:
-    """
-    Split an image into multiple views.
-    """
-    image = np.array(image)
-    alpha = image[..., 3]
-    alpha = np.any(alpha>0, axis=0)
-    start_pos = np.where(~alpha[:-1] & alpha[1:])[0].tolist()
-    end_pos = np.where(alpha[:-1] & ~alpha[1:])[0].tolist()
-    images = []
-    for s, e in zip(start_pos, end_pos):
-        images.append(Image.fromarray(image[:, s:e+1]))
-    return [preprocess_image(image) for image in images]
-
-
 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.
+    * Upload multiple images of an object from different views and click "Generate" to create a 3D asset.
     * 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: Experimental multi-image support and Gaussian file extraction.
     """)
     
     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.*
+                    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.*
                     """)
-            
+                    
             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)
@@ -289,8 +204,7 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
                     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")
+                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)
@@ -299,10 +213,11 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
             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.*
-                        """)
-
+            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)
@@ -311,74 +226,47 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
                 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:
+    with gr.Row(visible=True) as multiimage_example:
         examples_multi = gr.Examples(
             examples=prepare_multi_example(),
-            inputs=[image_prompt],
+            inputs=[multiimage_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]
-    )
-    
-    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],
+        inputs=[multiimage_prompt, 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],
@@ -396,12 +284,11 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
         lambda: gr.Button(interactive=True),
         outputs=[download_gs],
     )
-
+    
     model_output.clear(
         lambda: gr.Button(interactive=False),
         outputs=[download_glb],
     )
-    
 
 # Launch the Gradio app
 if __name__ == "__main__":
@@ -411,4 +298,4 @@ if __name__ == "__main__":
         pipeline.preprocess_image(Image.fromarray(np.zeros((512, 512, 3), dtype=np.uint8)))    # Preload rembg
     except:
         pass
-    demo.launch(show_error=True)  
+    demo.launch(show_error=True)