whatmodel.sh / video / Step-Video-TI2V

Step-Video-TI2V

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Step-Video-TI2V is an open-weights video model from StepFun, released March 2025. Licence: mit.

Catalogue identity notes

StepFun Step-Video-TI2V (stepfun-ai/stepvideo-ti2v, pinned 3d7471a). VideoArgus cites 'Step-Video [27, 14]' (the Step-Video-T2V and Step-Video-TI2V reports) with #P 29B; its TI2V leaderboard row is mapped to the Step-Video-TI2V 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 ↗

43.5±6.9comparison only: no current run option verifiedfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The video models ranked either side of Step-Video-TI2V, out of 139 with a score, then more from StepFun.

#modelscorewhereRAMreleased
90HunyuanVideo-I2V Tencent45±4local~57GB2025-03
91CogVideoX-5B Zhipu AI (THUDM)44±2api price unknown +local~13GB2024-08
92Step-Video-TI2V StepFun44±7comparison only2025-03
93Wan 2.1 I2V Turbo Alibaba43±7api price unknown2025-02
94Ray 2 Luma AI43±2comparison only2025-01
more from StepFun
89Step-Video-T2V StepFun45±7comparison only2025-02

see all video models · find the ones that fit your machine

$ what it's good at

other tests1 not in a task · 80% of its score
testresultvs the others in its rundifficultycountswhy
VideoArgus-Bench TI2V (rubric-grounded score)71.1% ✎█··▄▄▄▄····▄ beats 0/6easy · avg 77%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 80%blunt · at its level

$ 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… 80%

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

sourceresultsshare of the scorelicence
VideoArgus: Agentic Rubric-Grounded Unified Evaluation for Video Generation and Editing (arXiv:2608.05485v1)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 80%CC-BY-4.0
prior · pull toward the middle▇▇▇▇▇▇ 20%
weighted average= 43.5

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

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