whatmodel.sh / image / Stable Diffusion v1.3

Stable Diffusion v1.3

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

Stable Diffusion v1.3 is an open-weights image model from CompVis, released August 2022. Its published size is 0.86B parameters. Licence: creativeml-openrail-m.

Catalogue identity notes

CompVis/stable-diffusion-v1-3 checkpoint (HF repo created 2022-08-18, revision 159f26f); 860M UNet per the CompVis README; memory is the site's params x 2 bytes x 1.2 + 0.5 estimate, as for the other SD v1.x entries.

26.6±3.8#137 of 144 image modelsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

Score within the LMArena text-to-image comparison set only.

$ how it compares

The image models ranked either side of Stable Diffusion v1.3, out of 197 with a score, then more from CompVis.

#modelscorewhereRAMreleased
185Openjourney PromptHero28±2local~2.1GB2022-11
186Stable Diffusion v1.4 CompVis27±2local~2.1GB2022-08
187Stable Diffusion v1.3 CompVis27±4local~2.1GB2022-08
188Stable Diffusion v1.1 CompVis26±3local~2.1GB2022-08
189Stable Diffusion v1.2 CompVis26±3local~2.1GB2022-08
more from CompVis
106Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M) CompVis48±15local~7.5GB2022-04

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

$ what it's good at

text to image▃▅▅▃▄▄█▃▁▂▁▁ #122 of 126 * · 94% of its score · 1 test

Trails CogView2 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GenEval43.0% ✎▅█···▅▃▃▃··▃ beats 2/10easy · avg 79%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 94%at its level

$ where to run it

Other ways to run it

version

  1. Run it as published · needs ~2.6 GB, NVIDIA only · from huggingface.co/CompVis (official)
    uv run --with diffusers --with transformers --with accelerate --with torch python -c "import torch; from diffusers import StableDiffusionPipeline; p=StableDiffusionPipeline.from_pretrained('CompVis/stable-diffusion-v1-3', torch_dtype=torch.float16).to('cuda'); p('a cat holding a sign').images[0].save('out.png')"

Official weights and documentation: huggingface.co/CompVis ↗

$ how the score was worked out · GenEval authors' results: djg… 94%

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
GenEval authors' results: djghosh13/geneval README and arXiv 2310.11513v11▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 94%MIT (README); CC-BY-4.0 (arXiv 2310.11513v1)
prior · pull toward the middle▇▇ 6%
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