Realtime interactive generative models FTW!
Announcing a new 🌊 of details and features for Magenta RealTime, the open weights live music AI model from GDM!
* Live Jamming with audio input 🎤🎸🎵
* Personalize your own models 🔧
* Tech report 📜
Links below in the 🧵...
We did it — the first decentralized RL training of a 32B model is complete!
Full open-source release is coming in ~1 week, including: checkpoints, data and a detailed technical report.
I cannot imagine the upcoming 3-4 years from now, the pioneer music and sound-related AI models are groundbreaking. I just discovered "SingSong". It's Google's private research model for generating musical Backing-track from only vocal singing.
https://t.co/Rny6mVo30W
psychedelic flavors and ambient background noises in a huge music caldron. My favorite track from their latest album “The Totemist” is “Dark Hat” https://t.co/U1olZFFoUg
“Ak'chamel, The Giver Of Illness” is my recently discovered favorite experimental music band. I just blown away by their sounds. It’s really hard to describe their style but simply: Folklore elements of Turkish, Arabic, Mongolian, Russian and Shamanic music with experimental +