UniGenDet is a unified co-evolutionary framework that jointly optimizes image generation and generated-image detection in a single loop. By bridging generation and authenticity understanding through symbiotic multimodal self-attention, UniGenDet turns the traditional "generator vs. detector" arms race into a closed-loop collaboration.
This repository hosts the fine-tuned model weights for UniGenDet.
🔗 Links
- GitHub Repository (Code & Detailed Instructions): Zhangyr2022/UniGenDet
- Paper (arXiv): 2604.21904
- Project Website: UniGenDet Project Page
🚀 Getting Started
The UniGenDet model supports two main tasks:
- Text-to-Image Generation (
t2i) - AI-Generated Image Detection and Explanation (
detection)
To use these weights for generation, detection, or further fine-tuning, please refer to the official GitHub repository. The repository provides a comprehensive demo.py script for interactive inference.
Quick Inference Example Setup:
- Clone the GitHub repository:
git clone https://github.com/Zhangyr2022/UniGenDet.git - Install dependencies as outlined in the repo's
README.md. - Download the base BAGEL pretrained assets.
- Run
demo.pypointing to this Hugging Face model directory.
For complete installation, data preparation, training (GDUF/DIGA), and evaluation instructions, please consult the main GitHub repository.
Citation
@article{zhang2026unigendet,
title = {UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection},
author = {Zhang, Yanran and Zheng, Wenzhao and Li, Yifei and Yu, Bingyao and Zheng, Yu and Chen, Lei and Zhou, Jie and Lu, Jiwen},
journal = {CoRR},
volume = {abs/2604.21904},
year = {2026},
url = {[https://arxiv.org/abs/2604.21904](https://arxiv.org/abs/2604.21904)},
}