Microsoft's VASA-1 can deepfake a person with one photo and one audio track
Briefly

from Ars Technica1 week ago
On Tuesday, Microsoft Research Asia unveiled VASA-1, an AI model that can create a synchronized animated video of a person talking or singing from a single photo and an existing audio track.
Read at Ars Technica
[
add
]
[
|
|
]