whatmodel.sh / image / SSD-1B

SSD-1B

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

SSD-1B is an open-weights image model from Segmind, released October 2023. Its published size is 1.3B parameters. Licence: apache-2.0.

Catalogue identity notes

segmind/SSD-1B, a 1.3B-parameter distilled SDXL (model card).

36.1±3.6#118 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 SSD-1B, out of 197 with a score.

#modelscorewhereRAMreleased
159Show-o (show-o-demo-512) Show Lab, NUS36±3local~7.9GB2024-10
160DALL·E 2 OpenAI36±3comparison only2022-04
161SSD-1B Segmind36±4local~3.3GB2023-10
162JanusFlow-1.3B DeepSeek36±6comparison only2024-11
163PixArt-α (PixArt-XL-2-1024-MS) PixArt (Huawei Noah's Ark Lab et al.)36±2local~14GB2023-11

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

$ what it's good at

text to image▂▅▅▃▄▄█▃▁▂▁▁ #100 of 126 * · 94% of its score · 1 test

Beats Latent Diffusion text2img-large (LDM-KL-8-G, LAION-400M), VQ-Diffusion (ITHQ), Stable Diffusion XL 0.9 (base) here, though they rank higher overall. Trails PixArt-α (PixArt-XL-2-1024-MS) here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
EvalMuse-40K model ranking (FGA-BLIP2 overall alignment)2.93 / 5 ✎█▄·▄██▄▄█▄▄▄ beats 6/14easy · avg 3.83 / 5▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 94%at its level

$ where to run it

Other ways to run it

version

  1. Run it as published · needs ~3.6 GB, NVIDIA only · from huggingface.co/segmind (official)
    uv run --with diffusers --with transformers --with accelerate --with torch python -c "import torch; from diffusers import StableDiffusionXLPipeline; p=StableDiffusionXLPipeline.from_pretrained('segmind/SSD-1B', torch_dtype=torch.float16, use_safetensors=True, variant='fp16').to('cuda'); p(prompt='a cat holding a sign').images[0].save('out.png')"

Official weights and documentation: huggingface.co/segmind ↗

$ how the score was worked out · EvalMuse-40K: A Reliable and… 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
EvalMuse-40K: A Reliable and Fine-Grained Benchmark with Comprehensive Human Annotations for Text-to-Image Generation Model Evaluation (arXiv v2)1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 94%CC-BY-4.0
prior · pull toward the middle▇▇ 6%
weighted average= 36.1

$ 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