README.md

---
title: HY-Motion-1.0
emoji: 💃
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 4.44.0
app_file: gradio_app.py
pinned: false
short_description: Text-to-3D and Image-to-3D Generation
---


<p align="center">
  <img src="./assets/banner.png" alt="Banner" width="100%">
</p>

<div align="center">
  <a href="https://hunyuan.tencent.com/motion" target="_blank">
    <img src="https://img.shields.io/badge/Official%20Site-333399.svg?logo=homepage" height="22px" alt="Official Site">
  </a>
  <a href="https://huggingface.co/spaces/tencent/HY-Motion-1.0" target="_blank">
    <img src="https://img.shields.io/badge/%F0%9F%A4%97%20Demo-276cb4.svg" height="22px" alt="HuggingFace Space">
  </a>
  <a href="https://huggingface.co/tencent/HY-Motion-1.0" target="_blank">
    <img src="https://img.shields.io/badge/%F0%9F%A4%97%20Models-d96902.svg" height="22px" alt="HuggingFace Models">
  </a>
  <a href="https://arxiv.org/pdf/2512.23464" target="_blank">
    <img src="https://img.shields.io/badge/Report-b5212f.svg?logo=arxiv" height="22px" alt="ArXiv Report">
  </a>
  <a href="https://x.com/TencentHunyuan" target="_blank">
    <img src="https://img.shields.io/badge/Hunyuan-black.svg?logo=x" height="22px" alt="X (Twitter)">
  </a>
</div>


# HY-Motion 1.0: Scaling Flow Matching Models for 3D Motion Generation


<p align="center">
  <img src="./assets/teaser.png" alt="Teaser" width="90%">
</p>


## 🔥 News
- **Dec 30, 2025**: 🤗 We released the inference code and pretrained models of [HY-Motion 1.0](https://huggingface.co/tencent/HY-Motion-1.0). Please give it a try via our [HuggingFace Space](https://huggingface.co/spaces/tencent/HY-Motion-1.0) and our [Official Site](https://hunyuan.tencent.com/motion)!


## **Introduction**

**HY-Motion 1.0** is a series of text-to-3D human motion generation models based on Diffusion Transformer (DiT) and Flow Matching. It allows developers to generate skeleton-based 3D character animations from simple text prompts, which can be directly integrated into various 3D animation pipelines. This model series is the first to scale DiT-based text-to-motion models to the billion-parameter level, achieving significant improvements in instruction-following capabilities and motion quality over existing open-source models.

### Key Features
- **State-of-the-Art Performance**: Achieves state-of-the-art performance in both instruction-following capability and generated motion quality.

- **Billion-Scale Models**: We are the first to successfully scale DiT-based models to the billion-parameter level for text-to-motion generation. This results in superior instruction understanding and following capabilities, outperforming comparable open-source models.

- **Advanced Three-Stage Training**: Our models are trained using a comprehensive three-stage process:

    - *Large-Scale Pre-training*: Trained on over 3,000 hours of diverse motion data to learn a broad motion prior.

    - *High-Quality Fine-tuning*: Fine-tuned on 400 hours of curated, high-quality 3D motion data to enhance motion detail and smoothness.

    - *Reinforcement Learning*: Utilizes Reinforcement Learning from human feedback and reward models to further refine instruction-following and motion naturalness.



<p align="center">
  <img src="./assets/pipeline.png" alt="System Overview" width="100%">
</p>

<p align="center">
  <img src="./assets/arch.png" alt="Architecture" width="100%">
</p>

<p align="center">
  <img src="./assets/sotacomp.png" alt="ComparisonSoTA" width="100%">
</p>


## 🔗 BibTeX

If you found this repository helpful, please cite our reports:

```bibtex
@article{hymotion2025,
  title={HY-Motion 1.0: Scaling Flow Matching Models for Text-To-Motion Generation},
  author={Tencent Hunyuan 3D Digital Human Team},
  journal={arXiv preprint arXiv:2512.23464},
  year={2025}
}
```

## Acknowledgements

We would like to thank the contributors to the [FLUX](https://github.com/black-forest-labs/flux), [diffusers](https://github.com/huggingface/diffusers), [HuggingFace](https://huggingface.co), [SMPL](https://smpl.is.tue.mpg.de/)/[SMPLH](https://mano.is.tue.mpg.de/), [CLIP](https://github.com/openai/CLIP), [Qwen3](https://github.com/QwenLM/Qwen3), [PyTorch3D](https://github.com/facebookresearch/pytorch3d), [kornia](https://github.com/kornia/kornia), [transforms3d](https://github.com/matthew-brett/transforms3d), [FBX-SDK](https://www.autodesk.com/developer-network/platform-technologies/fbx-sdk-2020-0), [GVHMR](https://zju3dv.github.io/gvhmr/), and [HunyuanVideo](https://github.com/Tencent-Hunyuan/HunyuanVideo) repositories or tools, for their open research and exploration.