whatmodel.sh / image / Stable Diffusion XL 0.9 (base)

Stable Diffusion XL 0.9 (base)

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

Stable Diffusion XL 0.9 (base) is an open-weights image model from Stability AI, released June 2023. Its published size is 3.5B parameters. Licence: sdxl-0.9-research.

Catalogue identity notes

stabilityai/stable-diffusion-xl-base-0.9 (gated, non-commercial research licence). Stability's announcement: 3.5B-parameter base model; minimum 8 GB VRAM (RTX 20-series). The separate 'SDXL Refiner 0.9' benchmark row (base+refiner pipeline) is not mapped to this model.

39.8±6.3#108 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 XL 0.9 (base), out of 197 with a score, then more from Stability AI.

#modelscorewhereRAMreleased
146Show-o2 1.5B-HQ Show Lab, NUS40±3local~7.9GB2025-06
147Skywork UniPic 1.5B Skywork AI40±6comparison only2025-07
148Stable Diffusion XL 0.9 (base) Stability AI40±6local~4.9GB2023-06
149Stable Diffusion 3 Medium Stability AI40±2api $0.035/image +local~11GB2024-06
150Kolors Kuaishou (Kolors team)39±3local~22GB2024-07
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
152Stable Cascade Stability AI38±4local~13GB2024-02

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

$ what it's good at

text to image▂▅▅▃▄▄█▃▁▂▁▁ #104 of 126 * · 83% of its score · 2 tests

Beats Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M), VQ-Diffusion (ITHQ) here, though they rank higher overall. Trails Emu3, PixArt-α (PixArt-XL-2-1024-MS), SSD-1B here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
WISE (WiScore overall, GPT-4o judge)43.0% ✎▄·▆▂▆█▄▆▂▄·▄ beats 9/22medium · avg 60%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 82%at its level
HPS v2 benchmark (4-style average)27.7% ✎▃··▃▅·▅·▅▅█▅ beats 13/14hard · avg 27%▇ 1.1%blunt · at its level

$ where to run it

Other ways to run it

version

  1. Run it as published · needs ~8.9 GB, NVIDIA only · from stability.ai (official)
    uv run --with diffusers --with transformers --with accelerate --with torch python -c "import torch; from diffusers import DiffusionPipeline; p=DiffusionPipeline.from_pretrained('stabilityai/stable-diffusion-xl-base-0.9', torch_dtype=torch.float16, use_safetensors=True).to('cuda'); p('a cat holding a sign').images[0].save('out.png')"

Official weights and documentation: huggingface.co/stabilityai ↗

$ how the score was worked out · WISE: A World Knowledge-Infor… 82%, tgxs002/HPSv2 repository READ… 1%

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
WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation (arXiv v4)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 82%CC-BY-SA-4.0
tgxs002/HPSv2 repository README, HPS v2 benchmark table1▇ 1%Apache-2.0
prior · pull toward the middle▇▇▇▇▇ 17%
weighted average= 39.8

$ 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