A short demo-style transcript (YouTube) describing Microsoft’s VASA-1 system, which converts a single photograph (not a 3D scan or multi-angle set) into a lip-synced, controllable video avatar that can be scripted or driven in real time. Speakers demonstrate capabilities and discuss societal implications—convenience for introverts versus potential harms to human socialization.
What I'm about to show you is either going to terrify you or make you excited about the future.
Have you ever had maybe you're in that place right now where you want to turn your life around and you know somewhere deep in your soul there could be some decisions that you have to make.
So what you just saw is Vasa one from Microsoft. It takes a single photo, so not a 3D scan, not a hundred pictures from different angles, but one single photo, and turns that photo into a fully working video avatar. That avatar can then be given a script and be told to say anything. So this avatar can sync up in real time live with your voice. So I'd be able to talk and my avatar would be able to perform the actions for me and look like however I want it to look. This is my favorite comment about this technology. I used to dress up for work daily. Now I dress up for important video meetings. Soon I'll only dress up my avatar photo face to face. Interactions are becoming more and more distant, which is great if you're introverted like me, but maybe a disaster for the human race as a whole if we can't learn how to socialize. What do you think about this new kind of technology? Is this a positive or a scary future for humanity?