Towards a Simultaneous and Granular Identity-Expression Control in Personalized Face Generation

arXiv:2401.01207v2 Announce Type: replace
Abstract: In human-centric content generation, the pre-trained text-to-image models struggle to produce user-wanted portrait images, which retain the identity of individuals while exhibiting diverse expressions. This paper introduces our efforts towards personalized face generation. To this end, we propose a novel multi-modal face generation framework, capable of simultaneous identity-expression control and more fine-grained expression synthesis. Our expression control is so sophisticated that it can be specialized by the fine-grained emotional vocabulary. We devise a novel diffusion …

abstract arxiv content generation control cs.cv diverse face framework human human-centric identity image images modal multi-modal novel paper personalized struggle text text-to-image type