2024-10-04 - Movie Gen A Cast of Media Foundation Models

#video-generation

• 30b Transformer
  • text to image and text to video
  • trained on O(100M) videos and O(1B) images
  • tuned with Supervised Fine Tuning
• 13B video to audio and text to audio model
  • trained on O(1M) hours
• Flow Matching
• [ ]