whatmodel.sh / video / Cosmos-Predict2-14B-Video2World
Cosmos-Predict2-14B-Video2World
↗ share
+ contribute
Cosmos-Predict2-14B-Video2World is an open-weights video model from NVIDIA, released June 2025. Its published size is 14B parameters. Licence: nvidia-open-model-license.
Catalogue identity notes
NVIDIA Cosmos-Predict2 14B Video2World (image/video-conditioned) checkpoint, weights released 11 Jun 2025 (cosmos-predict2 README: 'We released post-training and inference code, along with model weights'); HF nvidia/Cosmos-Predict2-14B-Video2World pinned 03b03a3 (gated, automatic approval). PAI-Bench-G is image-conditioned generation and its Table 12 lists 'Cosmos-Predict2-14B' at 93 frames, 16 fps, 1280x704 (the Video2World default output), so the row maps to the Video2World checkpoint, not the separate Text2Image repo. Comparison-only: no local command verified in this pass.
Model information sources
Release date ↗ · Weights licence ↗
14B as named by NVIDIA (model name); repo gated (automatic approval), safetensors not read.
$ how it compares
The video models ranked either side of Cosmos-Predict2-14B-Video2World, out of 139 with a score, then more from NVIDIA.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 73 |  Seedance 1.0 Lite | 48±2 | comparison only | ||
| 74 | Cosmos-Predict2.5-2B | 48±2 | comparison only | ||
| 75 | Cosmos-Predict2-14B-Video2World | 48±8 | comparison only | ||
| 76 |  MAGI-1 24B | 48±4 | comparison only | ||
| 77 |  Kandinsky 6.0 Video Pro | 48±7 | local | ||
| more from NVIDIA | |||||
| 38 | Cosmos3-Super | 58±4 | local | ||
| 60 | Cosmos3-Nano | 52±3 | local | ||
| 72 | Cosmos-1.0-Diffusion-7B-Video2World | 49±5 | comparison only | ||
$ what it's good at
image to video▁▁▂▂██▄▃▃▄▂▂ #51 of 74 * · 73% of its score · 1 test
Beats HunyuanVideo 1.5, Wan 2.2 A14B, LTX-2 here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| PAI-Bench-G physical-AI video generation (Overall) | 80.0% ✎ | ▃······▅·█▅█ beats 5/10 | 73% |
$ where to run it
No verified API or download recorded yet · add one
Official weights and documentation: huggingface.co/nvidia ↗
$ how the score was worked out · PAI-Bench: A Comprehensive Be… 73%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 PAI-Bench: A Comprehensive Benchmark For Physical AI (arXiv:2512.01989v1) | 1 | 73% |
| prior · pull toward the middle | 27% | |
| weighted average | = 48.3 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json