Face2Diffusion for Fast and Editable Face Personalization

arXiv:2403.05094v1 Announce Type: new
Abstract: Face personalization aims to insert specific faces, taken from images, into pretrained text-to-image diffusion models. However, it is still challenging for previous methods to preserve both the identity similarity and editability due to overfitting to training samples. In this paper, we propose Face2Diffusion (F2D) for high-editability face personalization. The core idea behind F2D is that removing identity-irrelevant information from the training pipeline prevents the overfitting problem and improves editability of encoded faces. F2D consists of …

abstract arxiv cs.cv diffusion diffusion models face however identity image image diffusion images overfitting paper personalization samples text text-to-image training type