TensorX
返回文献探索

Paper · arXiv 2404.16022

PuLID: Pure and Lightning ID Customization via Contrastive Alignment

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

24 upvotesApril 24, 2024arXiv 预印本
AI 摘要

PuLID combines a Lightning T2I branch with a diffusion model to provide ID customization in text-to-image generation, maintaining ID fidelity and consistency in image elements.

Lightning T2Idiffusion modelcontrastive alignment lossaccurate ID lossID fidelityeditabilityimage elementsconsistency

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 (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

北京市昌平区探索星信息技术及软件开发工作室

京ICP备2026059466号
PuLID: Pure and Lightning ID Customization via Contrastive Alignment | TensorX