Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models

arXiv:2404.04243v1 Announce Type: new
Abstract: Text-to-image diffusion models have shown remarkable success in generating a personalized subject based on a few reference images. However, current methods struggle with handling multiple subjects simultaneously, often resulting in mixed identities with combined attributes from different subjects. In this work, we present MuDI, a novel framework that enables multi-subject personalization by effectively decoupling identities from multiple subjects. Our main idea is to utilize segmented subjects generated by the Segment Anything Model for both training …

arxiv cs.ai cs.cv identity image personalization text text-to-image type