Customize-A-Video: One-Shot Motion Customization of Text-to-Video Diffusion Models

arXiv:2402.14780v1 Announce Type: new
Abstract: Image customization has been extensively studied in text-to-image (T2I) diffusion models, leading to impressive outcomes and applications. With the emergence of text-to-video (T2V) diffusion models, its temporal counterpart, motion customization, has not yet been well investigated. To address the challenge of one-shot motion customization, we propose Customize-A-Video that models the motion from a single reference video and adapting it to new subjects and scenes with both spatial and temporal varieties. It leverages low-rank adaptation (LoRA) …

arxiv cs.cv customization diffusion diffusion models text text-to-video type video video diffusion