IDAdapter: Learning Mixed Features for Tuning-Free Personalization of Text-to-Image Models

arXiv:2403.13535v1 Announce Type: new
Abstract: Leveraging Stable Diffusion for the generation of personalized portraits has emerged as a powerful and noteworthy tool, enabling users to create high-fidelity, custom character avatars based on their specific prompts. However, existing personalization methods face challenges, including test-time fine-tuning, the requirement of multiple input images, low preservation of identity, and limited diversity in generated outcomes. To overcome these challenges, we introduce IDAdapter, a tuning-free approach that enhances the diversity and identity preservation in personalized image …

abstract arxiv avatars challenges cs.cv diffusion enabling face features fidelity fine-tuning free however image images mixed multiple personalization personalized portraits prompts stable diffusion test text text-to-image tool type