Meta's Movie Gen family of models includes a 30B parameter text-to-video generator and a 13B parameter text-to-audio generator capable of creating highly personalized videos and soundtracks.
The Movie Gen models can generate videos up to 16 seconds long, using natural language descriptions from users to create and modify scenes with personalized content.
Meta's focus is to empower content creators, expressing that the goal is 'to help people express themselves in new ways and to provide opportunities to people who might not otherwise have them.'
Movie Gen Audio is capable of generating music or sound effects for videos 'up to several minutes long,' providing customizable audio that enhances the video experience.
Collection
[
|
...
]