Microsoft's latest generative AI product just blew my mind by doing something I didn't think was possible. VASA-1 can combine a single image with one audio clip and turn it into a video of a person ...

Microsoft is showing off its AI chops with a new demo of its VASA-1, making Mona Lisa spit out rhymes like a rap star. The new framework is used for generating lifelike talking faces of virtual ...

Here’s another terrifying look into the future of AI, courtesy of Microsoft. Microsoft introduced the VASA-1 research project that can take a single image and an audio clip and transform it into a ...

Want smarter insights in your inbox? Sign up for our weekly newsletters to get only what matters to enterprise AI, data, and security leaders. Subscribe Now Microsoft has taken a major leap in the ...

A new AI model by Microsoft Research Asia, VASA-1, can create incredibly realistic deepfakes based only on a single photograph and one voice sample. The model easily beats anything available today.

Microsoft researchers have come up with a way to turn an image of someone into a video of them lip-syncing to an unrelated audio clip. The framework they came up with is called VASA-1. They wrote that ...