Abstract
Character Animation aims to generating character videos from still images through driving signals. Currently, diffusion models have become the mainstream in visual generation research, owing to their robust generative capabilities. However, challenges persist in the realm of image-to-video, especially in character animation, where temporally maintaining consistency with detailed information from character remains a formidable problem. In this paper, we leverage the power of diffusion models and propose a novel framework tailored for character animation. To preserve consistency of intricate appearance features from reference image, we design ReferenceNet to merge detail features via spatial attention. To ensure controllability and continuity, we introduce an efficient pose guider to direct character’s movements and employ an effective temporal modeling approach to ensure smooth inter-frame transitions between video frames. By expanding the training data, our approach can animate arbitrary characters, yielding superior results in character animation compared to other image-to-video methods. Furthermore, we evaluate our method on benchmarks for fashion video and human dance synthesis, achieving state-of-the-art results.
Paper: https://arxiv.org/pdf/2311.17117.pdf
ProjectPage: https://humanaigc.github.io/animate-anyone/
100% using this willy nilly or on someone without their consent will be illegal.
And anyone who has ever done anything compromising on video now has a great get out of jail free card.
Yep, for me this all seems like the early days of piracy before the laws all caught up. Trust me folks, the laws are coming. Doesn’t mean they’ll stop it, but it’ll be illegal
And even if some people are okay with it they’re obviously going to try to get money off of it.
It is already illegal to use someone’s likeliness without their permission (with a few exceptions for news worthy events).