| Checkpoint | File | Size |
|---|---|---|
| Video branch | video_branch/best.pt |
95 MB |
| Audio + text branch | audio_text_branch/best.pt |
3.0 GB |
| AV Divergence MoE | av_fusion/best.pt |
2.5 GB |
Update (2026-09-29): The models were updated.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support