Attention Calibration for Disentangled Text-to-Image Personalization

arXiv:2403.18551v1 Announce Type: new
Abstract: Recent thrilling progress in large-scale text-to-image (T2I) models has unlocked unprecedented synthesis quality of AI-generated content (AIGC) including image generation, 3D and video composition. Further, personalized techniques enable appealing customized production of a novel concept given only several images as reference. However, an intriguing problem persists: Is it possible to capture multiple, novel concepts from one single reference image? In this paper, we identify that existing approaches fail to preserve visual consistency with the reference …

abstract aigc ai-generated content arxiv attention concept cs.cv generated however image image generation images novel personalization personalized production progress quality reference scale synthesis text text-to-image type unlocked video