whatmodel.sh / video / T2V-Turbo (MS)
T2V-Turbo (MS)
↗ share
+ contribute
T2V-Turbo (MS) is an open-weights video model from UC Santa Barbara, released May 2024. Licence: cc-by-4.0.
Catalogue identity notes
Comparison-only, proposed so the T2V-Turbo paper's VBench run counts. T2V-Turbo (MS) is the ModelScopeT2V-based sibling of catalogued T2V-Turbo (VC2); the paper (Table 1) reports both. Weights: https://huggingface.co/jiachenli-ucsb/T2V-Turbo-MS (sha 2c7a54678e803377949a3147db5d6b843b67a4fa, created 2024-05-29, cc-by-4.0).
$ how it compares
The video models ranked either side of T2V-Turbo (MS), out of 139 with a score, then more from UC Santa Barbara.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 102 |  Open-Sora Plan v1.3 (I2V) | 39±7 | local | ||
| 103 |  UniVideo | 39±3 | comparison only | ||
| 104 | T2V-Turbo (MS) | 39±6 | comparison only | ||
| 105 |  HunyuanVideo | 39±3 | api price unknown +local | ||
| 106 |  Pandora (world model) | 39±7 | comparison only | ||
| more from UC Santa Barbara | |||||
| 107 | T2V-Turbo-v2 | 38±5 | api price unknown +local | ||
| 109 | T2V-Turbo (VC2) | 38±3 | local | ||
$ what it's good at
text to video▇▅▄▆█▆▇▂▃▃▂▄ #64 of 94 * · 83% of its score · 1 test
Trails LTX-2.3, T2V-Turbo-v2 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| VBench (T2V total) lab | 80.6% ✎ | █···▄▄▄····▄ beats 0/5 | 83% |
$ where to run it
No verified API or download recorded yet · add one
Weights and documentation: huggingface.co/jiachenli-ucsb ↗
$ how the score was worked out · T2V-Turbo: Breaking the Quali… 83%
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 |
|---|---|---|
 T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback (arXiv:2405.18750v2) · lab-reported | 1 | 83% |
| prior · pull toward the middle | 17% | |
| weighted average | = 39.1 |
$ 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