[//]: # ( )
[//]: # ( )
[//]: # ( )
> Join our **[Wechat](#find-us)** and **[Discord](#find-us)** group to discuss and find help from us.
β Living out everyoneβs imagination on creating and manipulating 3D assets.β
## π₯ News
- Jan 21, 2025: π¬ Enjoy exciting 3D generation on our website [Hunyuan3D Studio](https://3d.hunyuan.tencent.com)!
- Jan 21, 2025: π¬ Release inference code and pretrained models
of [Hunyuan3D 2.0](https://huggingface.co/tencent/Hunyuan3D-2).
- Jan 21, 2025: π¬ Release Hunyuan3D 2.0. Please give it a try
via [huggingface space](https://huggingface.co/spaces/tencent/Hunyuan3D-2)
our [official site](https://3d.hunyuan.tencent.com)!
## **Abstract**
PolyGenixAI: Fast and High-Quality 3D Asset Generation
We present PolyGenixAI, an advanced system for rapidly generating high-resolution textured 3D assets. This system comprises two core components:
a high-speed shape generation model, PolyGenixAI-DiT, and a robust texture synthesis model, PolyGenixAI-Paint.
PolyGenixAI-DiT, a scalable flow-based diffusion transformer, delivers precise geometry aligned with input images in seconds,
enabling efficient creation of 3D models for diverse applications.
PolyGenixAI-Paint leverages strong geometric and diffusion priors to produce vibrant, high-resolution texture maps for both generated and user-provided meshes.
Additionally, PolyGenixAI Studio offers a user-friendly platform that simplifies 3D asset creation and manipulation.
It empowers both professionals and enthusiasts to quickly generate, edit, and animate 3D models with ease.
PolyGenixAI outperforms state-of-the-art models, delivering superior geometry details, condition alignment, and texture quality.
Optimized for speed, it ensures fast model generation without compromising quality, making it ideal for real-time and production workflows.
## β―οΈ **Hunyuan3D 2.0**
### Architecture
Hunyuan3D 2.0 features a two-stage generation pipeline, starting with the creation of a bare mesh, followed by the
synthesis of a texture map for that mesh. This strategy is effective for decoupling the difficulties of shape and
texture generation and also provides flexibility for texturing either generated or handcrafted meshes.
### Performance
We have evaluated Hunyuan3D 2.0 with other open-source as well as close-source 3d-generation methods.
The numerical results indicate that Hunyuan3D 2.0 surpasses all baselines in the quality of generated textured 3D assets
and the condition following ability.
| Model | CMMD(β¬) | FID_CLIP(β¬) | FID(β¬) | CLIP-score(β¬) |
|-------------------------|-----------|-------------|-------------|---------------|
| Top Open-source Model1 | 3.591 | 54.639 | 289.287 | 0.787 |
| Top Close-source Model1 | 3.600 | 55.866 | 305.922 | 0.779 |
| Top Close-source Model2 | 3.368 | 49.744 | 294.628 | 0.806 |
| Top Close-source Model3 | 3.218 | 51.574 | 295.691 | 0.799 |
| Hunyuan3D 2.0 | **3.193** | **49.165** | **282.429** | **0.809** |
Generation results of Hunyuan3D 2.0:
### Pretrained Models
| Model | Date | Huggingface |
|----------------------|------------|--------------------------------------------------------|
| Hunyuan3D-DiT-v2-0 | 2025-01-21 | [Download](https://huggingface.co/tencent/Hunyuan3D-2) |
| Hunyuan3D-Paint-v2-0 | 2025-01-21 | [Download](https://huggingface.co/tencent/Hunyuan3D-2) |
## π€ Get Started with Hunyuan3D 2.0
You may follow the next steps to use Hunyuan3D 2.0 via code or the Gradio App.
### Install Requirements
Please install Pytorch via the [official](https://pytorch.org/) site. Then install the other requirements via
```bash
pip install -r requirements.txt
# for texture
cd hy3dgen/texgen/custom_rasterizer
python3 setup.py install
cd hy3dgen/texgen/differentiable_renderer
bash compile_mesh_painter.sh
```
### API Usage
We designed a diffusers-like API to use our shape generation model - Hunyuan3D-DiT and texture synthesis model -
Hunyuan3D-Paint.
You could assess **Hunyuan3D-DiT** via:
```python
from hy3dgen.shapegen import Hunyuan3DDiTFlowMatchingPipeline
pipeline = Hunyuan3DDiTFlowMatchingPipeline.from_pretrained('tencent/Hunyuan3D-2')
mesh = pipeline(image='assets/demo.png')[0]
```
The output mesh is a [trimesh object](https://trimesh.org/trimesh.html), which you could save to glb/obj (or other
format) file.
For **Hunyuan3D-Paint**, do the following:
```python
from hy3dgen.texgen import Hunyuan3DPaintPipeline
from hy3dgen.shapegen import Hunyuan3DDiTFlowMatchingPipeline
# let's generate a mesh first
pipeline = Hunyuan3DDiTFlowMatchingPipeline.from_pretrained('tencent/Hunyuan3D-2')
mesh = pipeline(image='assets/demo.png')[0]
pipeline = Hunyuan3DPaintPipeline.from_pretrained('tencent/Hunyuan3D-2')
mesh = pipeline(mesh, image='assets/demo.png')
```
Please visit [minimal_demo.py](minimal_demo.py) for more advanced usage, such as **text to 3D** and **texture generation
for handcrafted mesh**.
### Gradio App
You could also host a [Gradio](https://www.gradio.app/) App in your own computer via:
```bash
python3 gradio_app.py
```
Don't forget to visit [Hunyuan3D](https://3d.hunyuan.tencent.com) for quick use, if you don't want to host yourself.
## π Open-Source Plan
- [x] Inference Code
- [x] Model Checkpoints
- [x] Technical Report
- [ ] ComfyUI
- [ ] TensorRT Version
## π BibTeX
If you found this repository helpful, please cite our reports:
```bibtex
@misc{hunyuan3d22025tencent,
title={Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation},
author={Tencent Hunyuan3D Team},
year={2025},
}
@misc{yang2024tencent,
title={Tencent Hunyuan3D-1.0: A Unified Framework for Text-to-3D and Image-to-3D Generation},
year={2024},
author={Tencent Hunyuan3D Team},
eprint={2411.02293},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
## Acknowledgements
We would like to thank the contributors to
the [DINOv2](https://github.com/facebookresearch/dinov2), [Stable Diffusion](https://github.com/Stability-AI/stablediffusion), [FLUX](https://github.com/black-forest-labs/flux), [diffusers](https://github.com/huggingface/diffusers), [HuggingFace](https://huggingface.co), [CraftsMan3D](https://github.com/wyysf-98/CraftsMan3D),
and [Michelangelo](https://github.com/NeuralCarver/Michelangelo/tree/main) repositories, for their open research and
exploration.
## Find Us
| Wechat Group | Xiaohongshu | X | Discord |
|--------------|-------------|---|---------|
| | | | |
## Star History
)
[//]: # ( 
)
> Join our **[Wechat](#find-us)** and **[Discord](#find-us)** group to discuss and find help from us.
