VASA-1: Lifelike audio-driven talking faces generated in real time
1–10 of 166 posts
Re: VASA-1: Lifelike audio-driven talking faces generated in real time
#2woah. so far not in the news. this is the only article https://www.ai-gen.blog/2024/04/microsoft-vasa-1-ai-technolo...
Re: VASA-1: Lifelike audio-driven talking faces generated in real time
#3Oh no. "Cameras on please!" will be replaced by "AI generated faces off please!" in teams.
Re: VASA-1: Lifelike audio-driven talking faces generated in real time
#4Holy shit these are really high quality and basically in realtime on a 4090. What a time to be alive.
Re: VASA-1: Lifelike audio-driven talking faces generated in real time
#5Holy shit these are really high quality and basically in realtime on a 4090. What a time to be alive.
It really is something. 40 FPS on a 4090, damn.
Re: VASA-1: Lifelike audio-driven talking faces generated in real time
#6I like the considerations topic.
There’s likely also a an unsaid statement. This is for us only and we’ll be the only ones making money from it with our definition of “safety” and “positive”.
Re: VASA-1: Lifelike audio-driven talking faces generated in real time
#7The GPU requirements for realtime video generation are very minimal in the grand scheme of things. Assault on reality itself.
Re: VASA-1: Lifelike audio-driven talking faces generated in real time
#8“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.”
Re: VASA-1: Lifelike audio-driven talking faces generated in real time
#9So an ugly person will be able to present his or her ideas on the same visual level as a beautiful person. Is this some sort of democratization?
Re: VASA-1: Lifelike audio-driven talking faces generated in real time
#10lol how does something like this get only 50ish votes but some hallucinating video slop generator from some of the other competitors gets thousands?