whatmodel.sh / image / Stable Diffusion v2.0

Stable Diffusion v2.0

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

Stable Diffusion v2.0 is an open-weights image model from Stability AI, released November 2022. Licence: openrail++.

Catalogue identity notes

Release-level identity, following the existing sd-2-1 precedent. No local command: Stability AI's official stabilityai/stable-diffusion-2 repository now returns 401; the only copies are unaffiliated community mirrors, which are not linked.

29.1±2.7comparison only: no current run option verifiedfrom 3 benchmark results across 3 sources

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

$ how it compares

The image models ranked either side of Stable Diffusion v2.0, out of 197 with a score, then more from Stability AI.

#modelscorewhereRAMreleased
179AnyEdit (AnySD) Zhejiang University / NUS (AnyEdit)30±4comparison only2025-02
180Stable Diffusion v2.1 Stability AI29±2comparison only2022-12
181Stable Diffusion v2.0 Stability AI29±3comparison only2022-11
182Versatile Diffusion v1.0 SHI Labs29±4local~7.2GB2022-11
183DALL·E Mega (minDALL-E) DALL·E Mini / minDALL-E29±4local~8GB2022-07
more from Stability AI
137Stable Diffusion 3.5 Large Stability AI42±1api $0.065/image +local~5.4GB2024-10
141Stable Diffusion 3.5 Medium Stability AI41±3api $0.035/image +local~20GB2024-10
148Stable Diffusion XL 0.9 (base) Stability AI40±6local~4.9GB2023-06

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

$ what it's good at

text to image▁▂▇▇▆▅█▇▂▃▁▁ #138 of 157 * · 49% of its score · 2 tests

Beats Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M), VQ-Diffusion (ITHQ), VILA-U 7B (256px) here, though they rank higher overall. Trails CogView2, Versatile Diffusion v1.0 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GenEval51.0% ✎▅█···▅▃▃▃··▃ beats 6/10easy · avg 79%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 49%at its level
HPS v2 benchmark (4-style average)27.2% ✎▃··▃▅·▅·▅▅█▅ beats 10/14hard · avg 27%▇ 0.2%blunt · at its level
other tests1 not in a task · 48% of its score
testresultvs the others in its rundifficultycountswhy
EvalAlign human text-image alignment score4.6400 mean human alignment score ✎█▄▄·█·▄█▄▄·▄ beats 3/11avg 6.285 mean human alignment score▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 48%typical

$ where to run it

No verified API or download recorded yet · add one

$ how the score was worked out · GenEval authors' results: djg… 49%, EvalAlign: Supervised Fine-Tu… 48%, tgxs002/HPSv2 repository READ… 0%

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)
EvalAlign: Supervised Fine-Tuning Multimodal LLMs with Human-Aligned Data for Evaluating Text-to-Image Models (arXiv:2406.16562v3)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 48%CC-BY-4.0
tgxs002/HPSv2 repository README, HPS v2 benchmark table1▇ 0%Apache-2.0
prior · pull toward the middle▇ 3%
weighted average= 29.1

$ 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