whatmodel.sh / video / VideoCrafter1 T2V

VideoCrafter1 T2V

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

VideoCrafter1 T2V is an open-weights video model from Tencent AI Lab / HKUST, released October 2023.

Catalogue identity notes

October 2023 VideoCrafter1 text-to-video, 1024×576, 16 frames; distinct from early VideoCrafter/LVDM and VideoCrafter2.

25.6±2.3#88 of 93 video modelsfrom 4 benchmark results across 1 source

$ how it compares

The video models ranked either side of VideoCrafter1 T2V, out of 139 with a score.

#modelscorewhereRAMreleased
131Runway Gen-2 Runway27±2comparison only2023-06
132PikaLab (September 2023) Pika27±2comparison only2023-09
133VideoCrafter1 T2V Tencent AI Lab / HKUST26±2local~8.1GB2023-10
134Show-1 Show Lab / NUS25±2local~83GB2023-10
135LVDM (text-to-video) HKUST / Tencent AI Lab25±3local~6.1GB2023-05

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

$ what it's good at

text to video▆▄▃▄▆▅█▃▂▂▂▄ #62 of 68 · 98% of its score · 4 tests

Beats Open-Sora 1.2 here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
EvalCrafter 2023 motion quality53.08 / 100 ✎▄····▄██··▄▄ beats 3/7very easy · avg 85.14 / 100▇▇▇▇▇▇▇▇▇▇ 26%at its level
EvalCrafter 2023 visual quality60.85 / 100 ✎▄█·····▄·█▄▄ beats 6/7very easy · avg 87.87 / 100▇▇▇▇▇▇▇▇▇▇ 25%at its level
EvalCrafter 2023 temporal consistency55.89 / 100 ✎▄···▄▄▄▄▄··█ beats 1/7very easy · avg 88.67 / 100▇▇▇▇▇▇▇▇▇▇ 24%at its level
EvalCrafter 2023 text-video alignment61.95 / 100 ✎▂··▂▂·····▂█ beats 6/7very easy · avg 87.86 / 100▇▇▇▇▇▇▇▇▇ 23%at its level

$ where to run it

Other ways to run it

  1. Run it as published · needs ~8.1 GB, NVIDIA only · from github.com/AILab-CVC (official)
    git clone https://github.com/AILab-CVC/VideoCrafter && cd VideoCrafter && git checkout a11f5ae2b18db91d2c1b191153ebc0c3a5dd87e8 && conda create -n videocrafter python=3.8.5 -y && conda activate videocrafter && pip install -r requirements.txt && mkdir -p checkpoints/base_1024_v1 && wget -O checkpoints/base_1024_v1/model.ckpt https://huggingface.co/VideoCrafter/Text2Video-1024/resolve/main/model.ckpt && sh scripts/run_text2video.sh

Official weights and documentation: github.com/AILab-CVC ↗

$ how the score was worked out · EvalCrafter: original 2023 te… 98%

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
EvalCrafter: original 2023 text-to-video evaluations4▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 98%CC-BY-4.0
prior · pull toward the middle▇ 2%
weighted average= 25.6

$ 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