Microsoft publishes paper on VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time
— AI Breakfast (@AiBreakfast) 19 avril 2024
VASA is capable of generating a large spectrum of expressive facial nuances and natural head motions
It can handle long-form audio and stably output seamless talking face videos: pic.twitter.com/FiBb11G1ru
Microsoft publishes paper on VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time VASA is capable of generating a large spectrum of expressive facial nuances and natural head motions It can handle long-form audio and stably output seamless talking face videos: