Microsoft has unveiled a new lip-syncing tool that transforms a still image of a person into an animated clip of them talking or singing.
Microsoft unveiled a new lip-syncing AI tool that transforms a still image of a person’s face into an animated clip of them talking or singing.
VASA is currently just a research demonstration with no plans to release the product or allow others to use the API; essentially, Microsoft just wants to show off its lip-syncing model. Microsoft demonstrated VASA by using DALL-E 3 or StyleGAN2 to generate AI images of people but real photographs could be used; the president of the United States, for example, could be made to something they didn’t say — raising ethical questions around deepfakes and misinformation.
United States Latest News, United States Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Microsoft VASA-1 AI turns photos into lifelike talking videos, and it’s insaneMicrosoft's new VASA-1 AI model can combine a portrait image with an audio file to create a high-quality video of someone talking.
Read more »
Ahead of Trans Visibility Day, Republicans got close to passing major anti-trans measuresKatelyn Burns is a freelance journalist based in New England. She was the first openly transgender Capitol Hill reporter in U.S. history.
Read more »
Trans Day of Visibility: We're Speaking Out For Our RightsIn this op-ed, trans youth and adults SpeakOUT for trans day of visibility as part of Lambda Legal's campaign to elevate trans and nonbinary voices.
Read more »
Movie Review: The People’s JokerTrans coming-of-age story filtered through superhero homage
Read more »
Florida’s Anti-Trans Bathroom Law Spurs Harrowing Vigilante AttacksA new law in Florida aimed at trans people accessing bathroom facilities owned by the state government is reportedly encouraging vigilantes to patrol private businesses too.
Read more »