whatmodel.sh / video / Open-Sora 1.2

Open-Sora 1.2

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

Open-Sora 1.2 is an open-weights video model from HPC-AI Tech, released June 2024. Its published size is 1.1B parameters. Licence: apache-2.0.

26.6±2.8#87 of 93 video modelsfrom 3 benchmark results across 3 sources

$ how it compares

The video models ranked either side of Open-Sora 1.2, out of 139 with a score, then more from HPC-AI Tech.

#modelscorewhereRAMreleased
128Lumiere (T2V) Google27±4comparison only2024-01
129DynamiCrafter (1024) CUHK / Tencent AI Lab (DynamiCrafter)27±4comparison only2024-02
130Open-Sora 1.2 HPC-AI Tech27±3local~39GB2024-06
131Runway Gen-2 Runway27±2comparison only2023-06
132PikaLab (September 2023) Pika27±2comparison only2023-09
more from HPC-AI Tech
95Open-Sora 2.0 HPC-AI Tech42±5local~55GB2025-03
121Open-Sora 1.1 HPC-AI Tech32±7local~14GB2024-04

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

$ what it's good at

text to video▆▄▃▄▆▅█▃▂▂▂▄ #64 of 68 * · 82% of its score · 2 tests

Trails Show-1, VideoCrafter1 T2V here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GenAI-Arena text-to-video (anonymous Elo)871.5 ✎▃▃···▅▃·▃▅·█ beats 1/10avg 1229▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 69%sharp
ChronoMagic-Bench-150 GPT4o-MTScore (time-lapse metamorphosis)50.0% ✎▄·▄█▄▄▄·▄·▄█ beats 2/10medium · avg 71%▇▇▇▇▇ 13%at its level
other tests1 not in a task · 15% of its score
testresultvs the others in its rundifficultycountswhy
WorldModelBench (human total)6.11 / 10 ✎▅··▅▃···▃··█ beats 0/8easy · avg 7.71 / 10▇▇▇▇▇▇ 15%at its level

$ where to run it

Other ways to run it

  1. Run it as published · needs ~39 GB, NVIDIA only · from github.com/hpcaitech (official)
    git clone https://github.com/hpcaitech/Open-Sora && cd Open-Sora && git checkout v1.2.0 && pip install -v . && python scripts/inference.py configs/opensora-v1-2/inference/sample.py --num-frames 4s --resolution 720p --aspect-ratio 9:16 --prompt "a beautiful waterfall"

Official weights and documentation: huggingface.co/hpcai-tech ↗

$ how the score was worked out · GenAI-Arena (TIGER-Lab) text-… 69%, WorldModelBench: Judging Vide… 15%, ChronoMagic-Bench: A Benchmar… 13%

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 leaderboard1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 69%MIT
WorldModelBench: Judging Video Generation Models As World Models1▇▇▇▇ 15%CC-BY-4.0
ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation1▇▇▇▇ 13%CC-BY-4.0
prior · pull toward the middle▇ 3%
weighted average= 26.6

$ 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