Downloads · 30 days
27
61% of all-time downloads
vjepa21-cosmos-predicted-4frames-adapter
Aaypom/vjepa21-cosmos-predicted-4frames-adapter
vjepa21-cosmos-predicted-4frames-adapter is a video-to-video model from Aaypom. Use it for the video-to-video task on the model card, and read the license before you ship it in a product. It is set up for pytorch.
This adapter maps two frozen V-JEPA 2.1 predicted tubelets covering four future frames into one Cosmos CV4 future latent slot. Frames 1-12 are context and frames 13-16 are predicted. Training uses latent L1 plus 0.1 c…
All-time downloads
44
Public
Repo size
29.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt2.1 GB · 100%
At a glance
- Task
- Video-to-Video
- Library
- pytorch
- Access
- Public
- Created
- Sep 20, 2026
- Updated
- Sep 20, 2026
- SHA
- e85f0391
Model card
From the Hugging Face model README
V-JEPA 2.1 predicted-latent to Cosmos adapter
This adapter maps two frozen V-JEPA 2.1 predicted tubelets covering four future frames into one Cosmos CV4 future latent slot. Frames 1-12 are context and frames 13-16 are predicted. Training uses latent L1 plus 0.1 cosine distance; no RGB loss is used. Upstream weights are excluded.
- V-JEPA checkpoint:
https://dl.fbaipublicfiles.com/vjepa2/vjepa2_1_vitg_384.pt - Cosmos tokenizer:
nvidia/Cosmos-0.1-Tokenizer-CV4x8x8 - Metrics:
metrics/latest.json
- Task
- Video-to-Video
- Library
- pytorch
- Created
- Sep 20, 2026
- Updated
- Sep 20, 2026