whatmodel.sh / image / Stable Diffusion v1.5

Stable Diffusion v1.5

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

Stable Diffusion v1.5 is an open-weights image model from Stability AI, released October 2022. Its published size is 0.86B parameters. Licence: creativeml-openrail-m.

Catalogue identity notes

Stable Diffusion 1.5. The original Runway repository is deprecated; this community mirror is the checkpoint used in the official Diffusers MPS guide. The mirror is unaffiliated with Runway. Memory estimates are planning estimates, not measured device requirements.

Model information sources

· Parameter count ↗

UNet only: HF Hub safetensors total for the official repo (pinned revision), 859,520,964 = unet/diffusion_pytorch_model.safetensors. The CLIP text encoder (123.06M) and VAE (83.65M) bring the pipeline to 1.066B; safety checker not counted. Observed 2026-10-07.

25.5±1.8#140 of 144 image modelsfrom 7 benchmark results across 7 sources

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

$ how it compares

The image models ranked either side of Stable Diffusion v1.5, out of 197 with a score, then more from Stability AI.

#modelscorewhereRAMreleased
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
192OneCAT-3B Meituan (OneCAT team)24±5local~25GB2025-09
193LCM Dreamshaper v7 SimianLuo (LCM authors)23±4local~1.7GB2023-10
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▃▅▅▃▄▄█▃▁▂▁▁ #124 of 126 · 70% of its score · 5 tests

Beats Stable Diffusion v1.2 here, though they rank higher overall. Trails CogView2 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
GenEval43.0% ✎▅█···▅▃▃▃··▃ beats 3/10easy · avg 79%▇▇▇▇▇▇▇▇▇ 21%at its level
EvalMuse-40K model ranking (FGA-BLIP2 overall alignment)2.25 / 5 ✎█▄·▄██▄▄█▄▄▄ beats 1/14easy · avg 3.83 / 5▇▇▇▇▇▇▇▇ 20%at its level
TIFA v1.0 (overall, mPLUG VQA)78.4% ✎█·······▄▄▄▄ beats 3/5very easy · avg 95%▇▇▇▇▇▇▇ 16%typical
GeckoNum Task 1: exact number generation (human-annotated)20.3% ✎██·█·······█ beats 0/3medium · avg 51%▇▇▇ 7.0%typical
WISE (WiScore overall, GPT-4o judge)32.0% ✎▄·▆▂▆█▄▆▂▄·▄ beats 4/22medium · avg 60%▇▇ 5.4%at its level
other tests2 not in a task · 28% of its score
testresultvs the others in its rundifficultycountswhy
EvalAlign human text-image alignment score4.4500 mean human alignment score ✎█▄▄·█·▄█▄▄·▄ beats 0/11avg 6.285 mean human alignment score▇▇▇▇▇▇▇▇ 21%typical
HEIM text-image alignment (aspect win rate, v1.1.0)53.1% ✎▁····█▁·▁··▁ beats 2/9very easy · avg 92%▇▇▇ 7.0%sharp · at its level · noisy

$ where to run it

Other ways to run it

version

  1. Run it as published · needs ~4 GB, NVIDIA only · from huggingface.co/docs
    uv run --with torch --with diffusers --with transformers --with accelerate --with safetensors python -c "import torch; from diffusers import StableDiffusionPipeline; p=StableDiffusionPipeline.from_pretrained('stable-diffusion-v1-5/stable-diffusion-v1-5', torch_dtype=torch.float16).to('cuda'); p.enable_attention_slicing(); p('A lighthouse at sunset', height=512, width=512).images[0].save('image.png')"

Weights and documentation: huggingface.co/stable-diffusion-v1-5 ↗

$ how the score was worked out · GenEval authors' results: djg… 21%, EvalAlign: Supervised Fine-Tu… 21%, EvalMuse-40K: A Reliable and… 20% and 4 more

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▇▇▇▇▇▇ 21%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▇▇▇▇▇▇ 21%CC-BY-4.0
EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation (arXiv v2)1▇▇▇▇▇▇ 20%CC-BY-4.0
TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering (arXiv v3)1▇▇▇▇▇ 16%CC-BY-4.0
HEIM: Holistic Evaluation of Text-to-Image Models (arXiv 2311.04287v1)1▇▇ 7%CC-BY-4.0
Evaluating Numerical Reasoning in Text-to-Image Models (GeckoNum, arXiv v3)1▇▇ 7%CC-BY-4.0
WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation (arXiv v4)1▇▇ 5%CC-BY-SA-4.0
prior · pull toward the middle▇ 1%
weighted average= 25.5

$ 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