whatmodel.sh / video / LTX-Video 0.9 (2B)

LTX-Video 0.9 (2B)

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

LTX-Video 0.9 (2B) is an open-weights video model from Lightricks, released November 2024. Its published size is 2B parameters. Licence: ltxv-rail-m.

31.8±3.2#83 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 LTX-Video 0.9 (2B), out of 139 with a score, then more from Lightricks.

#modelscorewhereRAMreleased
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
124Cosmos-1.0-Autoregressive-5B-Video2World NVIDIA31±5comparison only2025-01
125NOVA-0.6B T2V BAAI29±3local~9.3GB2024-12
more from Lightricks
53LTX-2.5 Lightricks53±6api $0.12/sec +local~14GB2026-08
70LTX-2 Lightricks49±2local~120GB2025-10
83LTX-2 19B Distilled Lightricks47±8api $0.020/sec +local~41GB2026-01

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

$ what it's good at

text to video▆▄▃▄▆▅█▃▂▂▂▄ #57 of 68 * · 96% of its score · 1 test

Beats Open-Sora 1.1 here, though they rank higher overall.

testresultvs the others in its rundifficultycountswhy
GenAI-Arena text-to-video (anonymous Elo)964.0 ✎▃▃···▅▃·▃▅·█ beats 2/10avg 1229▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 96%sharp

$ where to run it

Other ways to run it

version

  1. Run it as published · needs ~5.3 GB, NVIDIA only · from github.com/huggingface
    python -c "import torch;from diffusers import AutoencoderKLLTXVideo,LTXPipeline,LTXVideoTransformer3DModel;from diffusers.utils import export_to_video;u='https://huggingface.co/Lightricks/LTX-Video/ltx-video-2b-v0.9.safetensors';t=LTXVideoTransformer3DModel.from_single_file(u,torch_dtype=torch.bfloat16);v=AutoencoderKLLTXVideo.from_single_file(u,torch_dtype=torch.bfloat16);p=LTXPipeline.from_pretrained('Lightricks/LTX-Video',transformer=t,vae=v,torch_dtype=torch.bfloat16);p.enable_model_cpu_offload();export_to_video(p(prompt='A woman with long brown hair walks through a sunlit forest, cinematic',width=704,height=480,num_frames=121,num_inference_steps=50).frames[0],'ltx.mp4',fps=24)"

Official weights and documentation: huggingface.co/Lightricks ↗

$ how the score was worked out · GenAI-Arena (TIGER-Lab) text-… 96%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 96%MIT
prior · pull toward the middle▇ 4%
weighted average= 31.8

$ 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