NeurIPS 2024poster46 citations

PuLID: Pure and Lightning ID Customization via Contrastive Alignment

Zinan Guo, Yanze Wu, Zhuowei Chen, Lang chen, Peng Zhang, Qian HE

Abstract

We propose Pure and Lightning ID customization (PuLID), a novel tuning-free ID customization method for text-to-image generation. By incorporating a Lightning T2I branch with a standard diffusion one, PuLID introduces both contrastive alignment loss and accurate ID loss, minimizing disruption to the original model and ensuring high ID fidelity. Experiments show that PuLID achieves superior performance in both ID fidelity and editability. Another attractive property of PuLID is that the image elements (\eg, background, lighting, composition, and style) before and after the ID insertion are kept as consistent as possible. Codes and models are available at https://github.com/ToTheBeginning/PuLID

diffusioncontrollable image generationimage customization
BibTeX
@inproceedings{
guo2024pulid,
title={Pu{LID}: Pure and Lightning {ID} Customization via Contrastive Alignment},
author={Zinan Guo and Yanze Wu and Zhuowei Chen and Lang chen and Peng Zhang and Qian HE},
booktitle={The Thirty-eighth Annual Conference on Neural Information Processing Systems},
year={2024},
url={https://openreview.net/forum?id=E6ZodZu0HQ}
}