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. In the future, it could power virtual avatars that render locally and don't require video feeds—or allow anyone with similar tools to take a photo of a person found online and make them appear to say whatever they want.

---

Here we go again... What they are capable of creating with AI tech is incredible. I do enjoy the development of AI and all its uses that can be of help or entertainment for us.

Though it come with challenges. When general trust goes out the window some gatekeepers will take up the role to enforce trust and present themselves as the keeper and judge of truth, that worries me greatly. AI used extensively in the wrong way can lead to so much mistrust that someone has to come inn and enforce monopoly on trust. With that much power, temptations arise.

On the other hand, maybe we will learn to go back to analog for truth.
In any case, the need to learn how to be skeptical of any digital content only grow. Separating fake from real is a most needed skill set.

#AI #VASA1 #Deepfake
Microsoft’s VASA-1 can deepfake a person with one photo and one audio track