Update app.py

app.py

@@ -1,31 +1,42 @@
+import gradio as gr
+import spaces
+from gradio_litmodel3d import LitModel3D
+
+import os
+import shutil
+os.environ['SPCONV_ALGO'] = 'native'
+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.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_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)
@@ -51,13 +62,36 @@ 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'),
     )
     
@@ -65,6 +99,12 @@ def pack_state(gs: Gaussian, mesh: MeshExtractResult) -> dict:
 
 
 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,
@@ -79,7 +119,7 @@ def image_to_3d(
     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.
@@ -90,7 +130,6 @@ def image_to_3d(
         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.
@@ -131,7 +170,6 @@ def image_to_3d(
     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))]
     video_path = os.path.join(user_dir, 'sample.mp4')
-
     imageio.mimsave(video_path, video, fps=15)
     state = pack_state(outputs['gaussian'][0], outputs['mesh'][0])
     torch.cuda.empty_cache()
@@ -142,6 +180,16 @@ def image_to_3d(
 def extract_glb(
     state: dict,
     mesh_simplify: float,
+    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))
@@ -157,10 +205,8 @@ def extract_glb(
 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.
     """
@@ -225,6 +271,12 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
             
             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)
@@ -232,6 +284,7 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
 
             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)
             
@@ -245,7 +298,6 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
         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)
@@ -259,6 +311,11 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
         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,
         )
@@ -298,6 +355,7 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
 
     generate_btn.click(
         get_seed,
+        inputs=[randomize_seed, seed],
         outputs=[seed],
     ).then(
         image_to_3d,
@@ -314,6 +372,10 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
     )
 
     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],
     )
@@ -328,4 +390,17 @@ with gr.Blocks(delete_cache=(600, 600)) as demo:
     )
 
     model_output.clear(
-        lambda: gr.Button(interactive=False),
+        lambda: gr.Button(interactive=False),
+        outputs=[download_glb],
+    )
+    
+
+# Launch the Gradio app
+if __name__ == "__main__":
+    pipeline = TrellisImageTo3DPipeline.from_pretrained("JeffreyXiang/TRELLIS-image-large")
+    pipeline.cuda()
+    try:
+        pipeline.preprocess_image(Image.fromarray(np.zeros((512, 512, 3), dtype=np.uint8)))    # Preload rembg
+    except:
+        pass
+    demo.launch()