I Can't Believe This Is Real

EMO: Emote Portrait Alive - Generating
Expressive Portrait Videos with Audio2Video
Diffusion Model
EMO, an expressive audio-driven portrait-video generation frame-
work. Input a single reference image and the vocal audio, e.g. talking and singing,
our method can generate vocal avatar videos with expressive facial expressions, and
various head poses, meanwhile, we can generate videos with any duration depending
on the length of input audio.