Bringing the magic of audio generation to video generation. In the process, creating more synthetic data to drive the future of multimodal models! https://t.co/KmCBu31H01

— Nando de Freitas (@NandoDF) 17 juin 2024

Bringing the magic of audio generation to video generation. In the process, creating more synthetic data to drive the future of multimodal models!

→ View original post on X — @nandodf,