Meta
Meta has 2 models in this directory, covering music and sound and video generation.
Meta's AI research group publishes AudioCraft, a research library containing MusicGen (text-to-music), AudioGen (text-to-sound), EnCodec, MAGNeT, MusicGen Style, JASCO and AudioSeal. The code is MIT-licensed but the model weights are released under a non-commercial licence.
They publish both ways: 1 of 2 models catalogued here ship downloadable weights and the rest are API or app only.
At a glance
- Headquarters
- United States
- Founded
- 2004
- Models here
- 2
- Categories
- music, video
Their models in this directory
Meta Movie Gen (weights unreleased)
A research model family announced by Meta in October 2024 covering text-to-video, personalized video, instruction-based video editing and synchronized
Video generation
Meta MusicGen (AudioCraft)
MusicGen is Meta's open text-to-music model, distributed in the AudioCraft research library alongside AudioGen (text-to-sound), MAGNeT, MusicGen Style
Music and sound