Update app.py

app.py

@@ -9,10 +9,9 @@ from typing import *
 import torch
 import numpy as np
 import imageio
-from easydict import EasyDict as edict
 from PIL import Image
 from trellis.pipelines import TrellisImageTo3DPipeline
-from trellis.representations import Gaussian, MeshExtractResult
+from trellis.representations import MeshExtractResult
 from trellis.utils import render_utils, postprocessing_utils
 
 
@@ -67,44 +66,6 @@ def preprocess_images(images: List[Tuple[Image.Image, str]]) -> List[Image.Image
     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(),
-            '_rotation': gs._rotation.cpu().numpy(),
-            '_opacity': gs._opacity.cpu().numpy(),
-        },
-        'mesh': {
-            'vertices': mesh.vertices.cpu().numpy(),
-            'faces': mesh.faces.cpu().numpy(),
-        },
-    }
-    
-    
-def unpack_state(state: dict) -> Tuple[Gaussian, edict, str]:
-    gs = Gaussian(
-        aabb=state['gaussian']['aabb'],
-        sh_degree=state['gaussian']['sh_degree'],
-        mininum_kernel_size=state['gaussian']['mininum_kernel_size'],
-        scaling_bias=state['gaussian']['scaling_bias'],
-        opacity_bias=state['gaussian']['opacity_bias'],
-        scaling_activation=state['gaussian']['scaling_activation'],
-    )
-    gs._xyz = torch.tensor(state['gaussian']['_xyz'], device='cuda')
-    gs._features_dc = torch.tensor(state['gaussian']['_features_dc'], device='cuda')
-    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:
@@ -138,7 +99,7 @@ def generate_and_extract_glb(
     mesh_simplify: float,
     texture_size: int,
     req: gr.Request,
-) -> Tuple[dict, str, str, str]:
+) -> Tuple[str, str, str]:
     """
     Convert an image to a 3D model and extract GLB file.
 
@@ -156,7 +117,6 @@ def generate_and_extract_glb(
         texture_size (int): The texture resolution.
 
     Returns:
-        dict: The information of the generated 3D model.
         str: The path to the video of the 3D model.
         str: The path to the extracted GLB file.
         str: The path to the extracted GLB file (for download).
@@ -210,35 +170,10 @@ def generate_and_extract_glb(
     glb_path = os.path.join(user_dir, 'sample.glb')
     glb.export(glb_path)
     
-    # Pack state for optional Gaussian extraction
-    state = pack_state(gs, mesh)
-    
     torch.cuda.empty_cache()
-    return state, video_path, glb_path, glb_path
+    return video_path, glb_path, glb_path
 
 
-@spaces.GPU
-def extract_gaussian(state: dict, req: gr.Request) -> Tuple[str, str]:
-    """
-    Extract a Gaussian splatting file from the generated 3D model.
-    
-    This function is called when the user clicks "Extract Gaussian" button.
-    It converts the 3D model state into a .ply file format containing
-    Gaussian splatting data for advanced 3D applications.
-
-    Args:
-        state (dict): The state of the generated 3D model containing Gaussian data
-        req (gr.Request): Gradio request object for session management
-
-    Returns:
-        Tuple[str, str]: Paths to the extracted Gaussian file (for display and download)
-    """
-    user_dir = os.path.join(TMP_DIR, str(req.session_hash))
-    gs, _ = unpack_state(state)
-    gaussian_path = os.path.join(user_dir, 'sample.ply')
-    gs.save_ply(gaussian_path)
-    torch.cuda.empty_cache()
-    return gaussian_path, gaussian_path
 
 
 def prepare_multi_example() -> List[Image.Image]:
@@ -284,10 +219,9 @@ 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 & Extract GLB" to create a 3D asset and automatically extract the GLB file.
-    * If you want the Gaussian file as well, click "Extract Gaussian" after generation.
     * If the image has alpha channel, it will be used as the mask. Otherwise, we use `rembg` to remove the background.
     
-    ✨New: 1) Experimental multi-image support. 2) Gaussian file extraction.
+    ✨New: Experimental multi-image support.
     """)
     
     with gr.Row():
@@ -317,25 +251,18 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
                 multiimage_algo = gr.Radio(["stochastic", "multidiffusion"], label="Multi-image Algorithm", value="stochastic")
             
             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)
+                mesh_simplify = gr.Slider(0.3, 0.98, label="Simplify", value=0.95, step=0.01)
                 texture_size = gr.Slider(512, 2048, label="Texture Size", value=1024, step=512)
 
             generate_btn = gr.Button("Generate & Extract GLB", variant="primary")
-            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)
+            model_output = LitModel3D(label="Extracted GLB", 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)  
+            download_glb = gr.DownloadButton(label="Download GLB", 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:
@@ -391,29 +318,20 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
     ).then(
         generate_and_extract_glb,
         inputs=[image_prompt, multiimage_prompt, is_multiimage, seed, ss_guidance_strength, ss_sampling_steps, slat_guidance_strength, slat_sampling_steps, multiimage_algo, mesh_simplify, texture_size],
-        outputs=[output_buf, video_output, model_output, download_glb],
+        outputs=[video_output, model_output, download_glb],
     ).then(
-        lambda: tuple([gr.Button(interactive=True), gr.Button(interactive=True)]),
-        outputs=[extract_gs_btn, download_glb],
+        lambda: gr.Button(interactive=True),
+        outputs=[download_glb],
     )
 
     video_output.clear(
-        lambda: tuple([gr.Button(interactive=False), gr.Button(interactive=False), gr.Button(interactive=False)]),
-        outputs=[extract_gs_btn, download_glb, download_gs],
-    )
-    
-    extract_gs_btn.click(
-        extract_gaussian,
-        inputs=[output_buf],
-        outputs=[model_output, download_gs],
-    ).then(
-        lambda: gr.Button(interactive=True),
-        outputs=[download_gs],
+        lambda: gr.Button(interactive=False),
+        outputs=[download_glb],
     )
 
     model_output.clear(
-        lambda: tuple([gr.Button(interactive=False), gr.Button(interactive=False)]),
-        outputs=[download_glb, download_gs],
+        lambda: gr.Button(interactive=False),
+        outputs=[download_glb],
     )