EMO
EMO copied to clipboard
AVSpeech: Large-scale Audio-Visual Speech Dataset https://academictorrents.com/details/b078815ca447a3e4d17e8a2a34f13183ec5dec41/tech UPDATE In this work, we propose a large-scale, high-quality, and diverse video dataset with rich facial attribute annotations, named the High-Quality Celebrity Video Dataset...
https://github.com/MooreThreads/Moore-AnimateAnyone Backround - MooreThreads is chinese nvidia competitor - can convert cuda code https://www.theregister.com/2023/12/20/moore_threads_mtt_s4000_gpu/ This code seems like 70% there. **Please upvote** developers to implement EMO paper - https://github.com/MooreThreads/Moore-AnimateAnyone/issues/98 Obviously...
https://humanaigc.github.io/emote-portrait-alive/ Under Cross-Actor Performance. `The Jocker - 《Jocker 2019》` The Joker - 《Joker 2019》
比如关注永雏塔菲喵,关注永雏塔菲谢谢喵~
Don't you think that this technology will help hackers and other bad guys to use single reference image and do what ever they want with it. Deep fake will get...
这种模型开源可能会导致假造证据、造谣等违法犯罪的事情发生,个人开发者可能不管这些,但是大公司不能不考虑这些事情的。喊赶紧开源的难道都是AI卖课的?
别说了,v50 封官