whatmodel.sh / video / Open-Sora 1.1

Open-Sora 1.1

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

Open-Sora 1.1 is an open-weights video model from HPC-AI Tech, released April 2024. Its published size is 0.7B parameters. Licence: apache-2.0.

31.9±6.7#81 of 93 video modelsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The video models ranked either side of Open-Sora 1.1, out of 139 with a score, then more from HPC-AI Tech.

#modelscorewhereRAMreleased
119Cosmos-1.0-Autoregressive-4B NVIDIA34±5comparison only2025-01
120Pika 1.0 Pika32±3comparison only2023-11
121Open-Sora 1.1 HPC-AI Tech32±7local~14GB2024-04
122LaVie (base T2V) Shanghai AI Lab (Vchitect)32±2local~4.9GB2023-09
123LTX-Video 0.9 (2B) Lightricks32±3local~5.3GB2024-11
more from HPC-AI Tech
95Open-Sora 2.0 HPC-AI Tech42±5local~55GB2025-03
130Open-Sora 1.2 HPC-AI Tech27±3local~39GB2024-06

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

$ what it's good at

text to video▆▄▃▄▆▅█▃▂▂▂▄ #58 of 68 * · 81% of its score · 1 test

Trails LTX-Video 0.9 (2B), LaVie (base T2V) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
ChronoMagic-Bench-150 GPT4o-MTScore (time-lapse metamorphosis)51.4% ✎▄·▄█▄▄▄·▄·▄█ beats 4/10medium · avg 71%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 81%at its level

$ where to run it

Other ways to run it

  1. Run it as published · needs ~13.5 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-v1-1/inference/sample.py --prompt "A beautiful sunset over the city" --num-frames 32 --image-size 480 854

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

$ how the score was worked out · ChronoMagic-Bench: A Benchmar… 81%

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
ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 81%CC-BY-4.0
prior · pull toward the middle▇▇▇▇▇▇ 19%
weighted average= 31.9

$ 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