Hey Everyone,
Just a snippet for today I found interesting. While Google releases a lot of research, this one stuck out to me.
VLOGGER uses two AIs to work its magic:
Lipreader: predicts your movements based on audio
Animator: creates video frames from your photo and movement details.
A lot of companies are actually releasing similar things and similar capabilities that might obscure what synthetic media becomes on the internet.
Image to Video
Video Translation
Video editing
Vlogger is a research project and not yet available for public use, however it’s fairly interesting.
It reminds me a lot about what Ideogram is doing, Ideogram which is like the new Stability AI, but out of Toronto.
What is Google Vlogger?
VLOGGER is a novel framework to synthesize humans from audio. Given a single input image like the ones shown on the Å‘rst column, and a sample audio input, our method generates photorealistic and temporally coherent videos of the person talking and vividly moving.
What does this mean for the future of synthetic media? OpenAI can clone your voice from 15 seconds of audio now.
Keep reading with a 7-day free trial
Subscribe to Artificial Intelligence Learning 🤖🧠🦾 to keep reading this post and get 7 days of free access to the full post archives.