whatmodel.sh / video / NOVA-0.6B T2V

NOVA-0.6B T2V

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

NOVA-0.6B T2V is an open-weights video model from BAAI, released December 2024. Its published size is 0.6B parameters. Licence: apache-2.0.

Catalogue identity notes

BAAI/nova-d48w1024-osp480 (NOVA-0.6B text-to-video, 33x768x480; README 'Text to Video' model table), Apache-2.0 (repo and HF card). Not the NOVA text-to-image checkpoints (sd512/sdxl1024) and not BAAI's later URSA.

29.2±3.3#84 of 93 video modelsfrom 2 benchmark results across 1 source* thinly tested, treat the rank as provisional

$ how it compares

The video models ranked either side of NOVA-0.6B T2V, out of 139 with a score.

#modelscorewhereRAMreleased
123LTX-Video 0.9 (2B) Lightricks32±3local~5.3GB2024-11
124Cosmos-1.0-Autoregressive-5B-Video2World NVIDIA31±5comparison only2025-01
125NOVA-0.6B T2V BAAI29±3local~9.3GB2024-12
126ZeroScope v2 576w cerspense27±3local~7.9GB2023-06
127Hotshot-XL Hotshot27±2local~10GB2023-10

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

$ what it's good at

text to video▆▄▃▄▆▅█▃▂▂▂▄ #59 of 68 * · 95% of its score · 2 tests
testresultvs the others in its rundifficultycountswhy
AIGVE-60K human perception MOS (LOVE)41.2% ✎▄▄·█··█▄▄▄▄▄ beats 2/10easy · avg 73%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 60%at its level
AIGVE-60K human text-video correspondence MOS (LOVE)47.2% ✎▄▄·█▄█▄··▄▄▄ beats 2/10easy · avg 70%▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 35%at its level

$ where to run it

Other ways to run it

  1. Run it as published · needs ~9.3 GB, NVIDIA only · from github.com/baaivision
    git clone https://github.com/baaivision/NOVA && cd NOVA && pip install diffusers transformers accelerate imageio-ffmpeg omegaconf wandb && pip install . && python -c "import torch; from diffnext.pipelines import NOVAPipeline; from diffnext.utils import export_to_video; p=NOVAPipeline.from_pretrained('BAAI/nova-d48w1024-osp480', torch_dtype=torch.float16, trust_remote_code=True).to('cuda'); export_to_video(p('Many spotted jellyfish pulsating under water.', max_latent_length=9).frames[0], 'nova.mp4', fps=12)"

Official weights and documentation: huggingface.co/BAAI ↗

$ how the score was worked out · LOVE: Benchmarking and Evalua… 95%

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
LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation (AIGVE-60K)2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 95%CC-BY-4.0
prior · pull toward the middle▇ 5%
weighted average= 29.2

$ 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