Update app.py

app.py

@@ -1,10 +1,209 @@
 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
 
-# Add this constant definition
 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)
+    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': {
+            **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:
+    """
+    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,
+    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,
+        )
+    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))]
+    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()
+    return state, video_path
+
+@spaces.GPU(duration=90)
+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))
+    gs, mesh = unpack_state(state)
+    glb = postprocessing_utils.to_glb(gs, mesh, simplify=mesh_simplify, texture_size=texture_size, verbose=False)
+    glb_path = os.path.join(user_dir, 'sample.glb')
+    glb.export(glb_path)
+    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.
+    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')
+    gs.save_ply(gaussian_path)
+    torch.cuda.empty_cache()
+    return gaussian_path, gaussian_path
 
 with gr.Blocks(theme=gr.themes.Default(), delete_cache=(600, 600)) as demo:
     with gr.Row():
@@ -120,5 +319,4 @@ if __name__ == "__main__":
         pipeline.preprocess_image(Image.fromarray(np.zeros((512, 512, 3), dtype=np.uint8)))    # Preload rembg
     except:
         pass
-    demo.launch()
-        
+    demo.launch()