Update app.py

app.py

@@ -15,48 +15,236 @@ from trellis.utils import render_utils, postprocessing_utils
 from gradio_litmodel3d import LitModel3D
 
 
-def check_gpu():
-    """Check if CUDA GPU is available and properly initialized"""
-    if not torch.cuda.is_available():
-        raise RuntimeError(
-            "This application requires a CUDA-capable GPU to run. "
-            "No CUDA GPU was detected in your system."
-        )
+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))
+    print(f'Creating user directory: {user_dir}')
+    os.makedirs(user_dir, exist_ok=True)
     
-    # Print GPU information for debugging
-    gpu_count = torch.cuda.device_count()
-    print(f"Found {gpu_count} CUDA GPU(s)")
-    for i in range(gpu_count):
-        gpu_name = torch.cuda.get_device_name(i)
-        print(f"GPU {i}: {gpu_name}")
+def end_session(req: gr.Request):
+    user_dir = os.path.join(TMP_DIR, str(req.session_hash))
+    print(f'Removing user directory: {user_dir}')
+    shutil.rmtree(user_dir)
 
-    # Try to initialize CUDA
-    try:
-        torch.cuda.init()
-        current_device = torch.cuda.current_device()
-        print(f"Using GPU {current_device}: {torch.cuda.get_device_name(current_device)}")
-    except Exception as e:
-        raise RuntimeError(f"Failed to initialize CUDA: {str(e)}")
+def preprocess_image(image: Image.Image) -> Tuple[str, Image.Image]:
+    """
+    Preprocess the input image.
 
-# ... [rest of the code remains exactly the same until main] ...
+    Args:
+        image (Image.Image): The input image.
 
-if __name__ == "__main__":
-    # Check GPU availability first
-    check_gpu()
+    Returns:
+        str: uuid of the trial.
+        Image.Image: The preprocessed image.
+    """
+    processed_image = pipeline.preprocess_image(image)
+    return processed_image
+
+def pack_state(gs: Gaussian, mesh: MeshExtractResult, trial_id: str) -> 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(),
+        },
+        'trial_id': trial_id,
+    }
+    
+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, state['trial_id']
+
+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
+
+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,
+    req: gr.Request,
+) -> Tuple[dict, str, str, str]:
+    """
+    Convert an image to a 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))]
+    trial_id = str(uuid.uuid4())
+    video_path = os.path.join(user_dir, f"{trial_id}.mp4")
+    imageio.mimsave(video_path, video, fps=15)
+    
+    # Save full quality GLB
+    full_glb = postprocessing_utils.to_glb(
+        outputs['gaussian'][0], 
+        outputs['mesh'][0],
+        simplify=0.0,  # No simplification
+        texture_size=2048,  # Maximum texture resolution
+        verbose=False
+    )
+    full_glb_path = os.path.join(user_dir, f"{trial_id}_full.glb")
+    full_glb.export(full_glb_path)
     
-    # Initialize pipeline with explicit device setting
-    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
-    pipeline = TrellisImageTo3DPipeline.from_pretrained(
-        "JeffreyXiang/TRELLIS-image-large"
-    ).to(device)
+    state = pack_state(outputs['gaussian'][0], outputs['mesh'][0], trial_id)
+    return state, video_path, model_output, full_glb_path
+
+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.
+    """
+    user_dir = os.path.join(TMP_DIR, str(req.session_hash))
+    gs, mesh, trial_id = 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, f"{trial_id}.glb")
+    glb.export(glb_path)
+    return glb_path, glb_path
+
+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" to create a 3D asset
+    * You can download the full quality GLB immediately after generation
+    * Or create a reduced size version using the GLB Extraction Settings
+    """)
+    
+    with gr.Row():
+        with gr.Column():
+            image_prompt = gr.Image(label="Image Prompt", format="png", image_mode="RGBA", type="pil", height=300)
+            
+            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, 500, 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, 500, label="Sampling Steps", value=12, step=1)
+
+            generate_btn = gr.Button("Generate")
+            
+            with gr.Accordion(label="GLB Extraction Settings", open=False):
+                mesh_simplify = gr.Slider(0.0, 0.98, label="Simplify", value=0.95, step=0.01)
+                texture_size = gr.Slider(512, 2048, label="Texture Size", value=1024, step=512)
+            
+            extract_glb_btn = gr.Button("Extract Reduced GLB", interactive=False)
+
+        with gr.Column():
+            video_output = gr.Video(label="Generated 3D Asset", autoplay=True, loop=True, height=300)
+            model_output = LitModel3D(label="3D Model Preview", exposure=20.0, height=300)
+            with gr.Row():
+                download_full = gr.DownloadButton(label="Download Full-Quality GLB", interactive=False)
+                download_reduced = gr.DownloadButton(label="Download Reduced GLB", interactive=False)
+            
+    output_buf = gr.State()
+
+    # Example images
+    with gr.Row():
+        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,
+        )
+
+    # Event handlers
+    demo.load(start_session)
+    demo.unload(end_session)
     
+    image_prompt.upload(
+        preprocess_image,
+        inputs=[image_prompt],
+        outputs=[image_prompt],
+    )
+
+    generate_btn.click(
+        get_seed,
+        inputs=[randomize_seed, seed],
+        outputs=[seed],
+    ).then(
+        image_to_3d,
+        inputs=[image_prompt, seed, ss_guidance_strength, ss_sampling_steps, slat_guidance_strength, slat_sampling_steps],
+        outputs=[output_buf, video_output, model_output, download_full],
+    ).then(
+        lambda: (gr.Button(interactive=True), gr.Button(interactive=True), gr.Button(interactive=False)),
+        outputs=[download_full, extract_glb_btn, download_reduced],
+    )
+
+    extract_glb_btn.click(
+        extract_glb,
+        inputs=[output_buf, mesh_simplify, texture_size],
+        outputs=[model_output, download_reduced],
+    ).then(
+        lambda: gr.Button(interactive=True),
+        outputs=[download_reduced],
+    )
+
+if __name__ == "__main__":
+    pipeline = TrellisImageTo3DPipeline.from_pretrained("JeffreyXiang/TRELLIS-image-large")
+    pipeline.cuda()
     try:
-        # Use smaller test image and explicit device
-        test_img = np.zeros((256, 256, 3), dtype=np.uint8)
-        pipeline.preprocess_image(Image.fromarray(test_img))
-        del test_img
-    except Exception as e:
-        print(f"Warning: Failed to preload rembg: {str(e)}")
-    
-    # Launch the demo
+        pipeline.preprocess_image(Image.fromarray(np.zeros((512, 512, 3), dtype=np.uint8)))    # Preload rembg
+    except:
+        pass
     demo.launch()