Home

Awesome

<div align="center"> <h1> ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning </h1>

Weifeng Chen*, Jiacheng Zhang*, Jie Wu†, Hefeng Wu, Xuefeng Xiao, Liang Lin

(*Equal Contribution , † Project Lead)

ByteDance, Sun Yat-Sen University

<a href='https://idaligner.github.io/'><img src='https://img.shields.io/badge/Project-Page-blue'></a> <a href='https://arxiv.org/abs/2404.15449'><img src='https://img.shields.io/badge/ Paper-Arxiv-red'></a> GitHub Org's stars

<!-- [![HF Demo](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Space-yellow)](https://huggingface.co/spaces/) --> <!-- [![ComfyUI](https://img.shields.io/badge/ComfyUI-ResAdapter-blue)](https://github.com/jiaxiangc/ComfyUI-ResAdapter) --> <!-- ![visitors](https://visitor-badge.laobi.icu/badge?page_id=bytedance.res-adapter) --> <!-- <img src="assets/misc/dreamlike1.png" width="49.9%"><img src="assets/misc/dreamlike2.png" width="50%"> Comparison examples between resadapter and [dreamlike-diffusion-1.0](https://civitai.com/models/1274/dreamlike-diffusion-10). --> </div> <!-- <img src="assets/mm2024_id_aligner_pipeline_00-1.png" /> --> <img src="assets/vis_sdxl.jpg" />

Release

<!-- ## Quicktour We provide a standalone [example code](quicktour.py) to help you quickly use resadapter with diffusion models. <div align=center> --> <!-- </div> --> <!-- ## Star History [![Star History Chart](https://api.star-history.com/svg?repos=Weifeng-Chen/ID-Aligner&type=Date)](https://star-history.com/#Weifeng-Chen/ID-Aligner&Date) -->

Citation

If you find ID-Aligner useful for your research and applications, please cite us using this BibTeX:

@misc{chen2024idaligner,
      title={ID-Aligner: Enhancing Identity-Preserving Text-to-Image Generation with Reward Feedback Learning}, 
      author={Weifeng Chen and Jiacheng Zhang and Jie Wu and Hefeng Wu and Xuefeng Xiao and Liang Lin},
      year={2024},
      eprint={2404.15449},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

For any question, please feel free to contact us.