---
title: TeleStyle
canonical_url: "https://www.modelscope.cn/models/TeleAI/TeleStyle"
md_url: "https://www.modelscope.cn/models/TeleAI/TeleStyle.md"
repository: TeleAI/TeleStyle
last_updated: 2026-06-24
license: apache-2.0
pipeline_tag: any-to-any
tasks:
  - any-to-any
base_model:
  - Wan-AI/Wan2.1-T2V-1.3B
  - Qwen/Qwen-Image-Edit-2509
base_model_relation: finetune
parameters: 660.6M
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 120
stars: 1
tags:
  - video
  - image
  - stylization
---

# TeleStyle

> TeleStyle - TeleAI 在 ModelScope 开源的模型。TeleStyle: Content-Preserving Style Transfer in Images and Videos

TeleAI/TeleStyle 是 ModelScope 魔搭社区上的 660.6M 参数any-to-any模型，采用 apache-2.0 许可，基于 Wan-AI/Wan2.1-T2V-1.3B、Qwen/Qwen-Image-Edit-2509 构建。

- **Repository**: TeleAI/TeleStyle
- **License**: apache-2.0
- **Tasks**: any-to-any
- **Parameters**: 660.6M
- **Base model**: Wan-AI/Wan2.1-T2V-1.3B, Qwen/Qwen-Image-Edit-2509
- **Tags**: video, image, stylization
- **Downloads**: 120
- **Stars**: 1
- **Last updated**: 2026-06-24

Source: https://www.modelscope.cn/models/TeleAI/TeleStyle

---

<div align="center">

<h1><b>TeleStyle: Content-Preserving Style Transfer in Images and Videos</b></h1>

</div>

<div align="center">
Shiwen Zhang, Xiaoyan Yang, Bojia Zi, Haibin Huang, Chi Zhang, Xuelong Li
  <p>
    Institute of Artificial Intelligence, China Telecom (TeleAI)&nbsp;&nbsp;
  </p>
</div>

<p align="center">
  <a href='https://tele-ai.github.io/TeleStyle/'><img src='https://img.shields.io/badge/Project-Page-Green'></a>
  &nbsp;
  <a href="http://arxiv.org/abs/2601.20175"><img src="https://img.shields.io/static/v1?label=Arxiv&message=TeleStyle&color=red&logo=arxiv"></a>
  &nbsp;
  <a href='https://huggingface.co/Tele-AI/TeleStyle'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model-orange'></a>
  &nbsp;
  <a href="https://github.com/Tele-AI/TeleStyle">
    <img src="https://img.shields.io/badge/GitHub-Code-red?logo=github">
  </a>
</p>


## 🔔News
- [2026-06-10]: TeleStyle V2 Released [Code](https://github.com/Tele-AI/TeleStyleV2), [Model](https://huggingface.co/Tele-AI/TeleStyleV2), [Demo](https://huggingface.co/spaces/witcherderivia/TeleStyleV2).

- [2026-01-28]: TeleStyle V1 Released [Code](https://github.com/Tele-AI/TeleStyle), [Model](https://huggingface.co/Tele-AI/TeleStyle), [Paper](http://arxiv.org/abs/2601.20175).

## How to use

- Please refer to [**🔗 GitHub**](https://github.com/Tele-AI/TeleStyle) for usage.


## 🌟 Citation

If you find TeleStyle useful for your research and applications, please cite using this BibTeX:

```bibtex
@article{teleai2026telestyle,
    title={TeleStyle: Content-Preserving Style Transfer in Images and Videos}, 
    author={Shiwen Zhang and Xiaoyan Yang and Bojia Zi and Haibin Huang and Chi Zhang and Xuelong Li},
    journal={arXiv preprint arXiv:2601.20175},
    year={2026}
}
```