README.md

---
license: cc-by-nc-nd-4.0
base_model:
- black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
---

Official pre-trained model for UniCalli: A Unified Diffusion Framework for Column-Level Generation and Recognition of Chinese Calligraphy

<img src="teaser.png" width="100%" alt="">

[![arXiv](https://img.shields.io/badge/arXiv-2025.13745-b31b1b.svg)](https://arxiv.org/abs/2510.13745)
[![GitHub](https://img.shields.io/github/stars/EnVision-Research/unicalli?style=social)](https://github.com/EnVision-Research/UniCalli)


## Model Details

- **Base Architecture**: FLUX
- **Model Size**: ~23GB
- **Training Data**: Large-scale Chinese calligraphy dataset with column-level annotations
- **Supported Tasks**:
  - Column-level calligraphy generation
  - Calligraphy text recognition (OCR)


## License
For academic research and non-commercial use only. For commercial use, please contact the authors. 

本模型仅供学术研究、非商业使用，商业使用请联系作者。

### Key Features

- 🎨 **Unified Architecture**: First framework to unify column-level calligraphy generation and recognition
- ✍️ **Multi-Master Styles**: Supports diverse calligraphic styles, including Wang Xizhi (王羲之), Yan Zhenqing (颜真卿), Ouyang Xun (欧阳询), etc.
- 📚 **Densely Annotated Data**: Trained on large-scale calligraphy dataset with detailed annotations.

## Usage

### Download Model

```python
from huggingface_hub import hf_hub_download

# Download the model weights
model_path = hf_hub_download(
    repo_id="TSXu/UniCalli-base",
    filename="unicalli-base_cleaned.bin"
)
```

### Prerequisites
The full inference code and usage examples will be released soon. Please check the [GitHub repository](https://github.com/EnVision-Research/UniCalli) for updates.


## Citation

If you find UniCalli useful in your research, please consider citing:

```bibtex
@article{xu2025unicalli,
  title={UniCalli: A Unified Diffusion Framework for Column-Level Generation and Recognition of Chinese Calligraphy},
  author={Xu, Tianshuo and Wang, Kai and Chen, Zhifei and Wu, Leyi and Wen, Tianshui and Chao, Fei and Chen, Ying-Cong},
  journal={arXiv preprint arXiv:2025.13745},
  year={2025}
}
```

## Acknowledgments

This work builds upon the FLUX architecture and benefits from the rich heritage of Chinese calligraphy. We thank the calligraphy masters whose works made this research possible.