Upload 251 files

.gitattributes

@@ -1,35 +1,125 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+wheels/nvdiffrast-0.3.3-cp310-cp310-linux_x86_64.whl filter=lfs diff=lfs merge=lfs -text
+assets/example_image/0.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/1.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/102.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/104.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/105.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/111.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/113.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/115.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/116.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/117.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/121.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/122.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/123.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/124.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/125.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/126.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/127.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/137.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/138.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/140.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/141.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/142.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/145.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/147.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/15.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/150.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/151.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/152.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/153.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/154.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/156.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/157.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/16.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/161.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/162.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/164.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/166.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/171.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/176.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/179.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/182.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/22.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/26.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/3.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/30.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/34.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/38.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/4.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/43.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/44.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/46.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/48.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/54.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/55.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/60.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/68.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/69.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/70.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/71.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/72.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/74.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/76.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/77.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/78.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/79.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/83.png filter=lfs diff=lfs merge=lfs -text
+assets/example_image/9.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/character_1.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/character_2.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/character_3.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/mushroom_1.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/mushroom_2.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/mushroom_3.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/orangeguy_1.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/orangeguy_2.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/orangeguy_3.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/popmart_1.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/popmart_2.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/popmart_3.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/rabbit_1.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/rabbit_2.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/rabbit_3.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/tiger_1.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/tiger_2.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/tiger_3.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/yoimiya_1.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/yoimiya_2.png filter=lfs diff=lfs merge=lfs -text
+assets/example_multi_image/yoimiya_3.png filter=lfs diff=lfs merge=lfs -text
+wheels/diff_gaussian_rasterization-0.0.0-cp310-cp310-linux_x86_64.whl filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,14 +1,16 @@
----
-title: Hi3DGen CPU
-emoji: 👁
-colorFrom: red
-colorTo: red
-sdk: gradio
-sdk_version: 5.23.2
-app_file: app.py
-pinned: false
-license: gpl-2.0
-short_description: Hi3DGen-CPU
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Hi3DGen
+emoji: 🏢
+colorFrom: indigo
+colorTo: blue
+sdk: gradio
+sdk_version: 4.44.1
+app_file: app.py
+pinned: false
+license: mit
+short_description: High-fidelity 3D Geometry Generation from images
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+Paper: 

app.py

@@ -0,0 +1,245 @@
+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 PIL import Image
+from trellis.pipelines import TrellisImageTo3DPipeline
+from trellis.utils import render_utils
+import trimesh
+import tempfile
+
+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 preprocess_mesh(mesh_prompt):
+    print("Processing mesh")
+    trimesh_mesh = trimesh.load_mesh(mesh_prompt)
+    trimesh_mesh.export(mesh_prompt+'.glb')
+    return mesh_prompt+'.glb'
+
+def preprocess_image(image):
+    if image is None:
+        return None
+    image = pipeline.preprocess_image(image, resolution=1024)
+    return image
+
+# Removed @spaces.GPU decorator to allow CPU execution
+def generate_3d(image, seed=-1,  
+                ss_guidance_strength=3, ss_sampling_steps=50,
+                slat_guidance_strength=3, slat_sampling_steps=6,):
+    if image is None:
+        return None, None, None
+
+    if seed == -1:
+        seed = np.random.randint(0, MAX_SEED)
+    
+    image = pipeline.preprocess_image(image, resolution=1024)
+    normal_image = normal_predictor(image, resolution=768, match_input_resolution=True, data_type='object')
+
+    outputs = pipeline.run(
+        normal_image,
+        seed=seed,
+        formats=["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,
+        },
+    )
+    generated_mesh = outputs['mesh'][0]
+    
+    # Save outputs
+    import datetime
+    output_id = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
+    os.makedirs(os.path.join(TMP_DIR, output_id), exist_ok=True)
+    mesh_path = f"{TMP_DIR}/{output_id}/mesh.glb"
+    
+    render_results = render_utils.render_video(generated_mesh, resolution=1024, ssaa=1, num_frames=8, pitch=0.25, inverse_direction=True)
+    def combine_diagonal(color_np, normal_np):
+        # Convert images to numpy arrays
+        h, w, c = color_np.shape
+        # Create a boolean mask that is True for pixels where x > y (diagonally)
+        mask = np.fromfunction(lambda y, x: x > y, (h, w))
+        mask = mask.astype(bool)
+        mask = np.stack([mask] * c, axis=-1)
+        # Where mask is True take color, else normal
+        combined_np = np.where(mask, color_np, normal_np)
+        return Image.fromarray(combined_np)
+
+    preview_images = [combine_diagonal(c, n) for c, n in zip(render_results['color'], render_results['normal'])]
+    
+    # Export mesh
+    trimesh_mesh = generated_mesh.to_trimesh(transform_pose=True)
+
+    trimesh_mesh.export(mesh_path)
+
+    return preview_images, normal_image, mesh_path, mesh_path
+
+def convert_mesh(mesh_path, export_format):
+    """Download the mesh in the selected format."""
+    if not mesh_path:
+        return None
+    
+    # Create a temporary file to store the mesh data
+    temp_file = tempfile.NamedTemporaryFile(suffix=f".{export_format}", delete=False)
+    temp_file_path = temp_file.name
+    
+    new_mesh_path = mesh_path.replace(".glb", f".{export_format}")
+    mesh = trimesh.load_mesh(mesh_path)
+    mesh.export(temp_file_path)  # Export to the temporary file
+    
+    return temp_file_path # Return the path to the temporary file
+
+# Create the Gradio interface with improved layout
+with gr.Blocks(css="footer {visibility: hidden}") as demo:
+    gr.Markdown(
+        """
+        <h1 style='text-align: center;'>Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging</h1>
+        <p style='text-align: center;'>
+            <strong>V0.1, Introduced By 
+            <a href="https://gaplab.cuhk.edu.cn/" target="_blank">GAP Lab</a> from CUHKSZ and 
+            <a href="https://www.nvsgames.cn/" target="_blank">Game-AIGC Team</a> from ByteDance</strong>
+        </p>
+        """
+    )
+    
+    with gr.Row():
+        gr.Markdown("""
+                    <p align="center">
+                    <a title="Website" href="https://stable-x.github.io/Hi3DGen/" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+                        <img src="https://www.obukhov.ai/img/badges/badge-website.svg">
+                    </a>
+                    <a title="arXiv" href="https://stable-x.github.io/Hi3DGen/hi3dgen_paper.pdf" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+                        <img src="https://www.obukhov.ai/img/badges/badge-pdf.svg">
+                    </a>
+                    <a title="Github" href="https://github.com/Stable-X/Hi3DGen" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+                        <img src="https://img.shields.io/github/stars/Stable-X/Hi3DGen?label=GitHub%20%E2%98%85&logo=github&color=C8C" alt="badge-github-stars">
+                    </a>
+                    <a title="Social" href="https://x.com/ychngji6" target="_blank" rel="noopener noreferrer" style="display: inline-block;">
+                        <img src="https://www.obukhov.ai/img/badges/badge-social.svg" alt="social">
+                    </a>
+                    </p>
+                    """)
+
+    with gr.Row():
+        with gr.Column(scale=1):
+            with gr.Tabs():
+                
+                with gr.Tab("Single Image"):
+                    with gr.Row():
+                        image_prompt = gr.Image(label="Image Prompt", image_mode="RGBA", type="pil")
+                        normal_output = gr.Image(label="Normal Bridge", image_mode="RGBA", type="pil")
+                        
+                with gr.Tab("Multiple Images"):
+                    gr.Markdown("<div style='text-align: center; padding: 40px; font-size: 24px;'>Multiple Images functionality is coming soon!</div>")
+                        
+            with gr.Accordion("Advanced Settings", open=False):
+                seed = gr.Slider(-1, MAX_SEED, label="Seed", value=0, step=1)
+                gr.Markdown("#### Stage 1: Sparse Structure Generation")
+                with gr.Row():
+                    ss_guidance_strength = gr.Slider(0.0, 10.0, label="Guidance Strength", value=3, step=0.1)
+                    ss_sampling_steps = gr.Slider(1, 50, label="Sampling Steps", value=50, 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=6, step=1)
+                    
+            with gr.Group():
+                with gr.Row():
+                    gen_shape_btn = gr.Button("Generate Shape", size="lg", variant="primary")
+                        
+        # Right column - Output
+        with gr.Column(scale=1):
+            with gr.Tabs():
+                with gr.Tab("Preview"):
+                    output_gallery = gr.Gallery(label="Examples", columns=4, rows=2, object_fit="contain", height="auto",show_label=False)
+                with gr.Tab("3D Model"):
+                    with gr.Column():
+                        model_output = gr.Model3D(label="3D Model Preview (Each model is approximately 40MB, may take around 1 minute to load)")
+                    with gr.Column():
+                        export_format = gr.Dropdown(
+                            choices=["obj", "glb", "ply", "stl"],
+                            value="glb",
+                            label="File Format"
+                        )
+                        download_btn = gr.DownloadButton(label="Export Mesh", interactive=False)
+    
+    image_prompt.upload(
+        preprocess_image,
+        inputs=[image_prompt],
+        outputs=[image_prompt]
+    )
+    
+    gen_shape_btn.click(
+        generate_3d,
+        inputs=[
+            image_prompt, seed,  
+            ss_guidance_strength, ss_sampling_steps,
+            slat_guidance_strength, slat_sampling_steps
+        ],
+        outputs=[output_gallery, normal_output, model_output, download_btn]
+    ).then(
+        lambda: gr.Button(interactive=True),
+        outputs=[download_btn],
+    )
+    
+    
+    def update_download_button(mesh_path, export_format):
+        if not mesh_path:
+            return gr.File.update(value=None, interactive=False)
+        
+        download_path = convert_mesh(mesh_path, export_format)
+        return download_path
+    
+    export_format.change(
+        update_download_button,
+        inputs=[model_output, export_format],
+        outputs=[download_btn]
+    ).then(
+        lambda: gr.Button(interactive=True),
+        outputs=[download_btn],
+    )
+    
+    examples = gr.Examples(
+        examples=[
+            f'assets/example_image/{image}'
+            for image in os.listdir("assets/example_image")
+        ],
+        inputs=image_prompt,
+    )
+
+    gr.Markdown(
+        """
+        **Acknowledgments**: Hi3DGen is built on the shoulders of giants. We would like to express our gratitude to the open-source research community and the developers of these pioneering projects:
+        - **3D Modeling:** Our 3D Model is finetuned from the SOTA open-source 3D foundation model [Trellis](https://github.com/microsoft/TRELLIS) and we draw inspiration from the teams behind [Rodin](https://hyperhuman.deemos.com/rodin), [Tripo](https://www.tripo3d.ai/app/home), and [Dora](https://github.com/Seed3D/Dora).
+        - **Normal Estimation:** Our Normal Estimation Model builds on the leading normal estimation research such as [StableNormal](https://github.com/hugoycj/StableNormal) and [GenPercept](https://github.com/aim-uofa/GenPercept).
+        
+        **Your contributions and collaboration push the boundaries of 3D modeling!**
+        """
+    )
+
+if __name__ == "__main__":
+    # Initialize pipeline
+    pipeline = TrellisImageTo3DPipeline.from_pretrained("Stable-X/trellis-normal-v0-1")
+    # Use CPU instead of GPU
+    pipeline.to("cpu")
+
+    # Initialize normal predictor
+    normal_predictor = torch.hub.load("hugoycj/StableNormal", "StableNormal_turbo", trust_repo=True, yoso_version='yoso-normal-v1-8-1')
+    # Ensure normal predictor is on CPU
+    normal_predictor.to("cpu")
+    
+    # Launch the app
+    demo.launch()