The First AI-Generated Video That Looks Super Real Microsoft Research announced VASA-1. It takes a single portrait photo and speech audio and produces a hyper-realistic talking face video with precise lip-audio sync, lifelike facial behavior, and naturalistic head movements generated in real-time. This is amazing, given that the AI-generated video looks very real! Of course, these examples will likely be cherry-picked, but this is still amazing. My favorite use-case for this tech is to revive old actors like Cary Grant in new movies with this tech :)
@bindureddy You haven't yet seen @HeyGen_Official . Almost every video of me on my timeline in the last 6 months is AI-produced.
The movement definitely has an uncanny valley sort of feel. It’s impressive for sure but I’m fearful of the ramifications technology like this will have. Especially when it reaches a point of being entirely indistinguishable from real life, which is already dangerously close to. AI is already regularly being used to undermine working artists, so this is only going to add to the chaos.
Getting there, but I’m also being trained to spot the tells. Hard to describe in words, but these type of AI-driven videos always show an invisible “net” that I see pulling across the face whenever a non-neutral expression is made. It’s like it’s all being pulled together, so it feels uniformly stretched.
@bindureddy @WarrenWhitlock Interesting but still a bit off. For example, it's eyes are not looking at the watcher.
@bindureddy where can i test this out with my own photos?
@bindureddy This explains a lot. It looks like most Hollywood actors from the past 15 years.
@bindureddy Two tells for me 1) the violent head jerks are unrealistic 2) the teeth change size as the avatar is speaking
@bindureddy Great, I bet MS Teams using all our daily video calls for training purposes! 😅
@bindureddy Nope still uncanny valley. There’s too many tells but it’s mostly in the subtle eye movements which are not natural.