DreamSalon: A Staged Diffusion Framework for Preserving Identity-Context in Editable Face Generation

arXiv:2403.19235v1 Announce Type: new
Abstract: While large-scale pre-trained text-to-image models can synthesize diverse and high-quality human-centered images, novel challenges arise with a nuanced task of "identity fine editing": precisely modifying specific features of a subject while maintaining its inherent identity and context. Existing personalization methods either require time-consuming optimization or learning additional encoders, adept in "identity re-contextualization". However, they often struggle with detailed and sensitive tasks like human face editing. To address these challenges, we introduce DreamSalon, a noise-guided, staged-editing …

abstract arxiv challenges context cs.cv diffusion diverse editing face features framework human identity image images novel personalization quality scale text text-to-image type