Update app.py

app.py

@@ -32,34 +32,9 @@ def end_session(req: gr.Request):
 
 
 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
-
-
 def pack_state(gs: Gaussian, mesh: MeshExtractResult) -> dict:
     return {
         'gaussian': {
@@ -110,66 +85,29 @@ def get_seed(randomize_seed: bool, seed: int) -> int:
 @spaces.GPU
 def image_to_3d(
     image: Image.Image,
-    multiimages: List[Tuple[Image.Image, str]],
-    is_multiimage: bool,
     seed: int,
     ss_guidance_strength: float,
     ss_sampling_steps: int,
     slat_guidance_strength: float,
     slat_sampling_steps: int,
-    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(
-            image,
-            seed=seed,
-            formats=["gaussian", "mesh"],
-            preprocess_image=False,
-            sparse_structure_sampler_params={
-                "steps": ss_sampling_steps,
-                "cfg_strength": ss_guidance_strength,
-            },
-            slat_sampler_params={
-                "steps": slat_sampling_steps,
-                "cfg_strength": slat_guidance_strength,
-            },
-        )
-    else:
-        outputs = pipeline.run_multi_image(
-            [image[0] for image in multiimages],
-            seed=seed,
-            formats=["gaussian", "mesh"],
-            preprocess_image=False,
-            sparse_structure_sampler_params={
-                "steps": ss_sampling_steps,
-                "cfg_strength": ss_guidance_strength,
-            },
-            slat_sampler_params={
-                "steps": slat_sampling_steps,
-                "cfg_strength": slat_guidance_strength,
-            },
-            mode=multiimage_algo,
-        )
+    outputs = pipeline.run(
+        image,
+        seed=seed,
+        formats=["gaussian", "mesh"],
+        preprocess_image=False,
+        sparse_structure_sampler_params={
+            "steps": ss_sampling_steps,
+            "cfg_strength": ss_guidance_strength,
+        },
+        slat_sampler_params={
+            "steps": slat_sampling_steps,
+            "cfg_strength": slat_guidance_strength,
+        },
+    )
+   
     video = render_utils.render_video(outputs['gaussian'][0], num_frames=120)['color']
     video_geo = render_utils.render_video(outputs['mesh'][0], num_frames=120)['normal']
     video = [np.concatenate([video[i], video_geo[i]], axis=1) for i in range(len(video))]
@@ -187,17 +125,7 @@ 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 +137,7 @@ 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')
@@ -225,21 +145,6 @@ def extract_gaussian(state: dict, req: gr.Request) -> Tuple[str, str]:
     torch.cuda.empty_cache()
     return gaussian_path, gaussian_path
 
-
-def prepare_multi_example() -> List[Image.Image]:
-    multi_case = list(set([i.split('_')[0] for i in os.listdir("assets/example_multi_image")]))
-    images = []
-    for case in multi_case:
-        _images = []
-        for i in range(1, 4):
-            img = Image.open(f'assets/example_multi_image/{case}_{i}.png')
-            W, H = img.size
-            img = img.resize((int(W / H * 512), 512))
-            _images.append(np.array(img))
-        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.
@@ -269,14 +174,7 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
             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.*
-                    """)
-            
+                    
             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)
@@ -288,8 +186,7 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
                 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):
@@ -311,7 +208,6 @@ 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
@@ -327,15 +223,6 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
             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)
@@ -345,21 +232,12 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
         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,
@@ -367,7 +245,7 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
         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=[image_prompt, seed, ss_guidance_strength, ss_sampling_steps, slat_guidance_strength, slat_sampling_steps],
         outputs=[output_buf, video_output],
     ).then(
         lambda: tuple([gr.Button(interactive=True), gr.Button(interactive=True)]),