EMO issues

fyi - Audio-Visual Speech Dataset training dataset - 4700 hours - 1.5tb torrent

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...

johndpope

fyi - referencenet project (with training code) based off previous paper HumanAIGC/AnimateAnyone - https://github.com/MooreThreads/Moore-AnimateAnyone

2

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...

johndpope

carbonium14

Cyber Security Concerns

3

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...

humzawaheed