GitHub · Python
OpenMOSS/OmniVAE
A unified audio-video variational autoencoder with cross-modal alignment for joint reconstruction and generation
- Stars
- 102
- Forks
- 5
- Stars gained in 24 hours
- +4
- Forks gained in 24 hours
- +1
Topics: audio-generation, audio-video-generation, dit, video-generation, vaes, audio, video, multimodal-generation, audio-video, representation-learning
Latest data point: Nov 22, 2026 · 102 stars · 5 forks