README.md

---
license: cc-by-nc-4.0
---

<!-- markdownlint-disable first-line-h1 -->
<!-- markdownlint-disable html -->
<!-- markdownlint-disable no-duplicate-header -->

<div align="center">
  <img src="assets/antgroup-logo.png" width="18%" alt="Ant Group Logo" />
</div>

<hr>
<p align="center">
  <a href="https://github.com/venus-guangjian/Venus-DeFakerOne/blob/main/DeFakerOne_paper.pdf"><b>📄 Local PDF</b></a> |
  <a href="https://arxiv.org/abs/2605.14091"><b>📄 arXiv</b></a> |
  <a href="https://huggingface.co/venus-guangjian/Venus-DeFakerOne"><b>🤗 Hugging Face</b></a> |
  <a href="https://github.com/venus-guangjian/Venus-DeFakerOne"><b>💻 GitHub</b></a>
</p>
<h2 align="center" style="white-space: nowrap;">
  <span style="color:#0369ff;">Venus-DeFakerOne</span>: Unified Fake Image <br> Detection &amp; Localization
</h2>




<p align="center">
<img src="assets/teaser.png" style="width: 1000px" align="center">
</p>
<p align="center">
<a href="https://github.com/venus-guangjian/Venus-DeFakerOne/blob/main/DeFakerOne_paper.pdf">A unified foundation model for FIDL.</a>
</p>

## Release

- [Coming Soon] 🔥 The Venus-DeFakerOne API will be available soon.
- [2026/05/15] 📄 We release the technical report and project page.

## Contents

- [API Usage](#api-usage)
- [Citation](#citation)

## API Usage

The Venus-DeFakerOne API will be available soon.  

## Citation

```bibtex
@article{venus-defakerone,
      title={Venus-DeFakerOne: Unified Fake Image Detection & Localization}, 
      author={GuangJian Team},
      year={2026},
      eprint={2605.14091},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2605.14091}, 
}
```