PuLID: Pure and Lightning ID Customization via Contrastive Alignment
Zhejiang University · ByteDance · University of Science and Technology of China · ByteDance Inc. · Institute of Remote Sensing Application, Chinese Academic of Sciences
PDF 由论文原始站点提供，PaperCompass 不保存论文文件。
摘要
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