PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models

arXiv:2312.13964v2 Announce Type: replace
Abstract: Recent advancements in personalized text-to-image (T2I) models have revolutionized content creation, empowering non-experts to generate stunning images with unique styles. While promising, adding realistic motions into these personalized images by text poses significant challenges in preserving distinct styles, high-fidelity details, and achieving motion controllability by text. In this paper, we present PIA, a Personalized Image Animator that excels in aligning with condition images, achieving motion controllability by text, and the compatibility with various personalized T2I …

abstract arxiv challenges cs.ai cs.cv experts fidelity generate image images modules personalized text text-to-image type via