The Mona Lisa rapping? New Microsoft AI animates faces from photos

The Mona Lisa can now be animated thanks to new artificial intelligence technology from Microsoft. Researchers have developed an AI model called VASA-1 that can create realistic videos of people speaking using a still image of their face and an audio clip. The technology can be used for education, accessibility, or creating virtual companions. However, concerns arise over potential misuse and the spread of misinformation. Microsoft has no immediate plans to release the model publicly, stating the need for responsible use and adherence to regulations. The AI tool recognizes natural face and head movements, resulting in lifelike videos, though some machine-generated traits are still noticeable.