Magic-Me: Identity-Specific Video Customized Diffusion

arXiv:2402.09368v2 Announce Type: replace
Abstract: Creating content with specified identities (ID) has attracted significant interest in the field of generative models. In the field of text-to-image generation (T2I), subject-driven creation has achieved great progress with the identity controlled via reference images. However, its extension to video generation is not well explored. In this work, we propose a simple yet effective subject identity controllable video generation framework, termed Video Custom Diffusion (VCD). With a specified identity defined by a few images, …

arxiv cs.ai cs.cv diffusion identity magic type video