Cosmos Predict 2.5 / Transfer 2.5
Predict 2.5-2B released 2025-10-06 (per model card); needs ~32.5 GB VRAM. Consolidated into Cosmos 3 (June 2026) but still downloadable.
- Input
- text, image, video
- Output
- video
- License
- NVIDIA Open Model License (commercial use allowed)
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| Hugging Face | nvidia/Cosmos-Predict2.5-2B | huggingface.co/nvidia/Cosmos-Predict2.5-2B | — |
| Hugging Face | nvidia/Cosmos-Predict2.5-14B | huggingface.co/nvidia/Cosmos-Predict2.5-14B | — |
| Hugging Face | nvidia/Cosmos-Transfer2.5-2B | huggingface.co/nvidia/Cosmos-Transfer2.5-2B | — |
| GitHub | — | github.com/nvidia-cosmos/cosmos-transfer2.5 | — |
Notable capabilities (2)
- Unified Text2World / Image2World / Video2World: Single diffusion transformer for physics-aware video world generation (720p, 16 fps, ~5 s clips) for robotics and AV synthetic data. source
- Multi-control world-to-world transfer: Transfer 2.5 generates world simulations conditioned on spatial controls (depth, segmentation, edges etc.) on top of Predict 2.5. source
Sources: Predict2.5-2B card, Transfer2.5 GitHub.
Other NVIDIA models
NVIDIA Nemotron 3.5 Lightning (30B-A3B) · NVIDIA NemotronLabs VoiceChat 11B (and PersonaPlex-7B) · NVIDIA Nemotron 3 Ultra (550B-A55B) · Cosmos 3 (Nano / Super) · NVIDIA Nemotron 3 Nano Omni (30B-A3B Reasoning) · Isaac GR00T N1.7 · NVIDIA Nemotron 3 Super (120B-A12B) · Cosmos Reason 2 · NVIDIA MagpieTTS Multilingual 357M · NVIDIA Parakeet / Canary / Nemotron Speech ASR (open) · Isaac GR00T N2 · Isaac GR00T N1 / N1.5 / N1.6