whatmodel.sh / video / Step-Video-T2V
Step-Video-T2V
↗ share
+ contribute
Step-Video-T2V is an open-weights video model from StepFun, released February 2025. Its published size is 30B parameters. Licence: mit.
Catalogue identity notes
StepFun Step-Video-T2V (stepfun-ai/stepvideo-t2v, pinned 7a2b639). VideoArgus cites 'Step-Video [27, 14]' (the Step-Video-T2V and Step-Video-TI2V reports) with #P 29B; its T2V leaderboard row is mapped to the Step-Video-T2V checkpoint, the only StepFun model for that input mode (the -Turbo T2V distillation is a separate repo and is not assumed). Comparison-only: local route not verified (multi-GPU).
Model information sources
Release date ↗ · Weights licence ↗ · Parameter count ↗
30B as stated by StepFun ('a state-of-the-art text-to-video pre-trained model with 30 billion parameters'); VideoArgus prints 29B.
$ how it compares
The video models ranked either side of Step-Video-T2V, out of 139 with a score, then more from StepFun.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 87 |  Hailuo 01 (MiniMax video-01 / I2V-01) | 46±4 | api $0.083/sec | ||
| 88 |  Kling 1.6 (Standard mode) | 45±5 | comparison only | ||
| 89 | Step-Video-T2V | 45±7 | comparison only | ||
| 90 |  HunyuanVideo-I2V | 45±4 | local | ||
| 91 |  CogVideoX-5B | 44±2 | api price unknown +local | ||
| more from StepFun | |||||
| 92 | Step-Video-TI2V | 44±7 | comparison only | ||
$ what it's good at
other tests1 not in a task · 81% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| VideoArgus-Bench T2V (rubric-grounded score) | 77.7% ✎ | █▄·▄█▄▄····▄ beats 2/8 | 81% |
$ where to run it
No verified API or download recorded yet · add one
Weights and documentation: huggingface.co/stepfun-ai ↗
$ how the score was worked out · VideoArgus: Agentic Rubric-Gr… 81%
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 |
|---|---|---|
 VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing (arXiv:2608.05485v1) | 1 | 81% |
| prior · pull toward the middle | 19% | |
| weighted average | = 44.7 |
$ 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