A Data Perspective on Enhanced Identity Preservation for Diffusion Personalization

arXiv:2311.04315v2 Announce Type: replace
Abstract: Large text-to-image models have revolutionized the ability to generate imagery using natural language. However, particularly unique or personal visual concepts, such as pets and furniture, will not be captured by the original model. This has led to interest in how to personalize a text-to-image model. Despite significant progress, this task remains a formidable challenge, particularly in preserving the subject's identity. Most researchers attempt to address this issue by modifying model architectures. These methods are capable …

abstract arxiv concepts cs.cv data diffusion furniture generate however identity image language natural natural language personalization perspective pets preservation text text-to-image type visual visual concepts will