Microsoft's VASA-1 generates lifelike avatars in real-time

Microsoft researchers have developed a process called VASA-1 that generates lifelike speaking faces for virtual AI avatars from photos and audio clips. The generated videos show natural mouth movements, facial expressions, and head movements in real-time.

The article Microsoft's VASA-1 generates lifelike avatars in real-time appeared first on THE DECODER.

ai avatars ai research article artificial intelligence audio avatars decoder generated generative-ai head microsoft movements natural photos process real-time researchers show speaking the decoder videos virtual