whatmodel.sh / image / Stable Diffusion v1.2

Stable Diffusion v1.2

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

Stable Diffusion v1.2 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-v1-2 checkpoint; 860M UNet per the CompVis README.

25.8±2.7#139 of 144 image modelsfrom 2 benchmark results across 2 sources* 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 v1.2, out of 197 with a score, then more from CompVis.

#modelscorewhereRAMreleased
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
190HiDream-E1.1 HiDream26±11comparison only2025-07
191Stable Diffusion v1.5 Stability AI26±2local~2.1GB2022-10
more from CompVis
106Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M) CompVis48±15local~7.5GB2022-04
186Stable Diffusion v1.4 CompVis27±2local~2.1GB2022-08

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

$ what it's good at

text to image▃▅▅▃▄▄█▃▁▂▁▁ #125 of 126 * · 97% of its score · 2 tests

Trails CogView2, Stable Diffusion v1.5 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GenEval44.0% ✎▅█···▅▃▃▃··▃ beats 4/10easy · avg 79%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 49%at its level
EvalMuse-40K model ranking (FGA-BLIP2 overall alignment)2.25 / 5 ✎█▄·▄██▄▄█▄▄▄ beats 0/14easy · avg 3.83 / 5▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 48%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-v1-2', 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… 49%, EvalMuse-40K: A Reliable and… 48%

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▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 49%MIT (README); CC-BY-4.0 (arXiv 2310.11513v1)
EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation (arXiv v2)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 48%CC-BY-4.0
prior · pull toward the middle▇ 3%
weighted average= 25.8

$ 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