Microsoft’s VASA-1 can deepfake a person with one photo and one audio track
Microsoft’s VASA-1 can deepfake a person with one photo and one audio track
YouTube videos of 6K celebrities helped train AI model to animate photos in real time.
YouTube videos of 6K celebrities helped train AI model to animate photos in real time.
"While acknowledging the possibility of misuse, it's imperative to recognize the substantial positive potential of our technique. The benefits – such as enhancing educational equity, improving accessibility for individuals with communication challenges, offering companionship or therapeutic support to those in need, among many others – underscore the importance of our research and other related explorations. We are dedicated to developing AI responsibly, with the goal of advancing human well-being.
Given such context, we have no plans to release an online demo, API, product, additional implementation details, or any related offerings until we are certain that the technology will be used responsibly and in accordance with proper regulations."
From the official page
Or until we have been made an offer we cannot refuse and pretend we didn’t see the bad actor who bought our technology using it exactly as could be predicted.
KillerTofu gets it.
ooo eee ooo...KILLER TOFU!
Why is that a thing they boast about? That is disgusting.
Yeah, this WILL be abused, inspite all good intentions that they might talk about
i’m not feeling any of this shit, bruv.