implement 3D model generation and extraction features with session management

app.py

@@ -8,6 +8,16 @@ from diffusers import DiffusionPipeline
 from transformers import pipeline, AutoTokenizer
 from huggingface_hub import login
 from PIL import Image
+from gradio_litmodel3d import LitModel3D
+import shutil
+os.environ['SPCONV_ALGO'] = 'native'
+from typing import *
+import imageio
+from easydict import EasyDict as edict
+from trellis.pipelines import TrellisImageTo3DPipeline
+from trellis.representations import Gaussian, MeshExtractResult
+from trellis.utils import render_utils, postprocessing_utils
+
 
 hf_token = os.getenv("hf_token")
 login(token=hf_token)
@@ -35,9 +45,23 @@ DEFAULT_NUM_INFERENCE_STEPS = 6
 DEFAULT_GUIDANCE_SCALE = 0.0
 DEFAULT_TEMPERATURE = 0.9
 
+TMP_DIR = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'tmp')
+os.makedirs(TMP_DIR, exist_ok=True)
+
 _text_gen_pipeline = None
 _image_gen_pipeline = None
 
+
+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)
+
+
 @spaces.GPU()
 def get_image_gen_pipeline():
     global _image_gen_pipeline
@@ -199,6 +223,147 @@ def preload_models():
     print(status)
     return success
 
+
+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
+
+
+@spaces.GPU
+def image_to_3d(
+    image: Image.Image,
+    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.
+        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))
+    
+    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))]
+    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
+
+
 # Create a combined function that handles the whole pipeline from example to image
 # This version gets the parameters from the UI components
 @spaces.GPU()
@@ -250,6 +415,13 @@ def create_interface():
             generated_image = gr.Image(show_label=False)
             gen3d_button = gr.Button("Create 3D visual with Trellis")
 
+            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)
+                download_gs = gr.DownloadButton(label="Download Gaussian", interactive=False)  
+    
             message_box = gr.Textbox(
                 label="Status Messages", 
                 interactive=False,
@@ -292,6 +464,23 @@ def create_interface():
                         step=1,
                         value=DEFAULT_NUM_INFERENCE_STEPS,
                     )
+                
+                with gr.Tab("3D Generation Settings"):
+                    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)
+
+                with gr.Tab("GLB Extraction Settings"):
+                    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)
+            
 
             # Examples section - simplified version that only updates the prompt fields
             gr.Examples(
@@ -317,8 +506,31 @@ def create_interface():
             outputs=[generated_image, message_box]
         )
 
+        gr.on(
+            triggers=[gen3d_button.click],
+            fn=image_to_3d,
+            inputs=[generated_image, seed, ss_guidance_strength, ss_sampling_steps, slat_guidance_strength, slat_sampling_steps, multiimage_algo],
+            outputs=[output_buf, video_output],
+        )
+
     return demo
 
 if __name__ == "__main__":
+    demo = create_interface()
+    demo.launch()
+    demo.load(start_session)
+    demo.unload(end_session)
+```
+
+if __name__ == "__main__":
+    # Initialize the Trellis pipeline before creating the interface
+    pipeline = TrellisImageTo3DPipeline.from_pretrained("JeffreyXiang/TRELLIS-image-large")
+    pipeline.cuda()
+    try:
+        # Preload rembg
+        pipeline.preprocess_image(Image.fromarray(np.zeros((512, 512, 3), dtype=np.uint8)))
+    except Exception as e:
+        print(f"Warning when preloading rembg: {e}")
+        
     demo = create_interface()
     demo.launch()