PuLID: Pure and Lightning ID Customization via Contrastive Alignment

Zinan Guo, Yanze Wu, Zhuowei_Chen, Lang Chen, Qian He

PuLID: Pure and Lightning ID Customization via Contrastive Alignment: 24 upvotes on Hugging Face Daily Papers, #2 of 9 papers on 2024-04-25. Day-by-day upvote history.

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 (e.g., background, lighting, composition, and style) before and after the ID insertion are kept as consistent as possible. Codes and models will be available at https://github.com/ToTheBeginning/PuLID

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.