Update app.py

app.py

@@ -1,7 +1,6 @@
 import gradio as gr
 import spaces
 from gradio_litmodel3d import LitModel3D
-
 import os
 import shutil
 os.environ['SPCONV_ALGO'] = 'native'
@@ -15,32 +14,33 @@ from trellis.pipelines import TrellisImageTo3DPipeline
 from trellis.representations import Gaussian, MeshExtractResult
 from trellis.utils import render_utils, postprocessing_utils
 
-
 MAX_SEED = np.iinfo(np.int32).max
 TMP_DIR = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'tmp')
 os.makedirs(TMP_DIR, exist_ok=True)
 
-
 def start_session(req: gr.Request):
     user_dir = os.path.join(TMP_DIR, str(req.session_hash))
     os.makedirs(user_dir, exist_ok=True)
-    
-    
+
 def end_session(req: gr.Request):
     user_dir = os.path.join(TMP_DIR, str(req.session_hash))
     shutil.rmtree(user_dir)
 
-
 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': {
-            **gs.init_params,
             '_xyz': gs._xyz.cpu().numpy(),
             '_features_dc': gs._features_dc.cpu().numpy(),
             '_scaling': gs._scaling.cpu().numpy(),
@@ -52,9 +52,8 @@ def pack_state(gs: Gaussian, mesh: MeshExtractResult) -> dict:
             'faces': mesh.faces.cpu().numpy(),
         },
     }
-    
-    
-def unpack_state(state: dict) -> Tuple[Gaussian, edict, str]:
+
+def unpack_state(state: dict) -> Tuple[Gaussian, edict]:
     gs = Gaussian(
         aabb=state['gaussian']['aabb'],
         sh_degree=state['gaussian']['sh_degree'],
@@ -68,19 +67,18 @@ def unpack_state(state: dict) -> Tuple[Gaussian, edict, str]:
     gs._scaling = torch.tensor(state['gaussian']['_scaling'], device='cuda')
     gs._rotation = torch.tensor(state['gaussian']['_rotation'], device='cuda')
     gs._opacity = torch.tensor(state['gaussian']['_opacity'], device='cuda')
-    
     mesh = edict(
         vertices=torch.tensor(state['mesh']['vertices'], device='cuda'),
         faces=torch.tensor(state['mesh']['faces'], device='cuda'),
     )
-    
     return gs, mesh
 
-
 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(
     multiimages: List[Tuple[Image.Image, str]],
@@ -92,22 +90,25 @@ def image_to_3d(
     multiimage_algo: Literal["multidiffusion", "stochastic"],
     req: gr.Request,
 ) -> Tuple[dict, str]:
+    """
+    Convert multiple images to a 3D model.
+    """
     user_dir = os.path.join(TMP_DIR, str(req.session_hash))
-        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_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,
+    )
     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))]
@@ -117,7 +118,6 @@ def image_to_3d(
     torch.cuda.empty_cache()
     return state, video_path
 
-
 @spaces.GPU(duration=90)
 def extract_glb(
     state: dict,
@@ -125,6 +125,9 @@ def extract_glb(
     texture_size: int,
     req: gr.Request,
 ) -> Tuple[str, str]:
+    """
+    Extract a GLB file from the 3D model.
+    """
     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)
@@ -133,9 +136,11 @@ def extract_glb(
     torch.cuda.empty_cache()
     return glb_path, glb_path
 
-
 @spaces.GPU
 def extract_gaussian(state: dict, req: gr.Request) -> Tuple[str, str]:
+    """
+    Extract a Gaussian file from the 3D model.
+    """
     user_dir = os.path.join(TMP_DIR, str(req.session_hash))
     gs, _ = unpack_state(state)
     gaussian_path = os.path.join(user_dir, 'sample.ply')
@@ -143,18 +148,17 @@ 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 = []
+        views = []
         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)))
+            views.append(img)
+        images.append(views)
     return images
 
 with gr.Blocks(delete_cache=(600, 600)) as demo:
@@ -208,30 +212,30 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
             with gr.Row():
                 download_glb = gr.DownloadButton(label="Download GLB", interactive=False)
                 download_gs = gr.DownloadButton(label="Download Gaussian", interactive=False)  
-    
+
     output_buf = gr.State()
-    
+
     # Example images at the bottom of the page
     with gr.Row(visible=True) as multiimage_example:
         examples_multi = gr.Examples(
             examples=prepare_multi_example(),
             inputs=[multiimage_prompt],
-            fn=split_image,
+            fn=lambda x: x,
             outputs=[multiimage_prompt],
             run_on_click=True,
             examples_per_page=8,
         )
-    
+
     # Handlers
     demo.load(start_session)
     demo.unload(end_session)
-    
+
     multiimage_prompt.upload(
         preprocess_images,
         inputs=[multiimage_prompt],
         outputs=[multiimage_prompt],
     )
-    
+
     generate_btn.click(
         get_seed,
         inputs=[randomize_seed, seed],
@@ -244,12 +248,12 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
         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],
@@ -258,7 +262,7 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
         lambda: gr.Button(interactive=True),
         outputs=[download_glb],
     )
-    
+
     extract_gs_btn.click(
         extract_gaussian,
         inputs=[output_buf],
@@ -267,7 +271,7 @@ 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],
@@ -281,4 +285,4 @@ 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)