whatmodel.sh / video / T2V-Turbo (VC2)

T2V-Turbo (VC2)

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

T2V-Turbo (VC2) is an open-weights video model from UC Santa Barbara, released May 2024. Licence: cc-by-4.0.

37.8±2.7#73 of 93 video modelsfrom 3 benchmark results across 3 sources

$ how it compares

The video models ranked either side of T2V-Turbo (VC2), out of 139 with a score, then more from UC Santa Barbara.

#modelscorewhereRAMreleased
107T2V-Turbo-v2 UC Santa Barbara38±5api price unknown +local~9.4GB2024-10
108Vidu 1.5 ShengShu (Vidu)38±3comparison only2024-11
109T2V-Turbo (VC2) UC Santa Barbara38±3local~9.4GB2024-05
110Runway Gen-4 Turbo Runway37±3api $0.050/sec2025-04
111MAGI-1 4.5B Sand AI37±5comparison only2025-04
more from UC Santa Barbara
104T2V-Turbo (MS) UC Santa Barbara39±6comparison only2024-05

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

$ what it's good at

text to video▆▄▃▄▆▅█▃▂▂▂▄ #51 of 68 · 97% of its score · 2 tests

Trails Pika 2.2, LTX-2.3 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GenAI-Arena text-to-video (anonymous Elo) lab1054.7 ✎▃▃···▅▃·▃▅·█ beats 7/10avg 1229▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%sharp
VBench (T2V total) lab +180.5% ✎█···▄▄▄····▄ beats 1/5very easy · avg 90%▇▇▇▇▇▇▇▇▇▇▇▇ 30%small run · several runs

$ where to run it

Other ways to run it

version

  1. Run it as published · needs ~9.4 GB, NVIDIA only · from github.com/Ji4chenLi
    git clone https://github.com/Ji4chenLi/t2v-turbo && cd t2v-turbo && pip install gradio==3.48.0 && hf download VideoCrafter/VideoCrafter2 model.ckpt --local-dir vc2 && hf download jiachenli-ucsb/T2V-Turbo-VC2 unet_lora.pt --local-dir t2v-turbo-vc2 && python app.py --unet_dir t2v-turbo-vc2/unet_lora.pt --base_model_dir vc2/model.ckpt --version v1

Weights and documentation: huggingface.co/jiachenli-ucsb ↗

$ how the score was worked out · GenAI-Arena (TIGER-Lab) text-… 67%, T2V-Turbo: Breaking the Quali… 15%, T2V-Turbo-v2: Enhancing Video… 15%

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
GenAI-Arena (TIGER-Lab) text-to-video leaderboard · lab-reported1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%MIT
T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback (arXiv:2405.18750v2) · lab-reported1▇▇▇▇▇ 15%CC-BY-4.0
T2V-Turbo-v2: Enhancing Video Generation Model Post-Training through Data, Reward, and Conditional Guidance Design (arXiv 2410.05677v3) · lab-reported1▇▇▇▇ 15%CC BY 4.0
prior · pull toward the middle▇ 3%
weighted average= 37.8

$ 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