whatmodel.sh / image / LCM-SSD-1B

LCM-SSD-1B

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

LCM-SSD-1B is an open-weights image model from latent-consistency, released November 2023. Its published size is 1.33B parameters. Licence: openrail++.

Catalogue identity notes

latent-consistency/lcm-ssd-1b (LCM distillation of SSD-1B). Memory estimated as for SSD-1B (1.3B).

Model information sources

· Parameter count ↗

UNet only: HF Hub safetensors total for the official UNet-only repo (pinned revision), 1,331,416,324 = diffusion_pytorch_model.safetensors; used with the segmind/SSD-1B pipeline, whose text encoders and VAE are not included. Observed 2026-10-07.

32.1±3.7#129 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 LCM-SSD-1B, out of 197 with a score, then more from latent-consistency.

#modelscorewhereRAMreleased
173UltraEdit (SD3, with mask) Peking University / BIGAI (UltraEdit)32±7comparison only2024-06
174VILA-U 7B (256px) MIT Han Lab / NVIDIA32±7local~20GB2024-10
175LCM-SSD-1B latent-consistency32±4local~3.6GB2023-11
176Janus-1.3B DeepSeek32±4local~5.5GB2024-10
177IF-M DeepFloyd31±3local~14GB2023-04
more from latent-consistency
168LCM-SDXL latent-consistency34±3local~8.9GB2023-11

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

$ what it's good at

text to image▂▅▅▃▄▄█▃▁▂▁▁ #114 of 126 * · 94% of its score · 1 test

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, Dreamlike Photoreal 2.0 here, though they rank lower overall.

testresultvs the others in its rundifficultycountswhy
EvalMuse-40K model ranking (FGA-BLIP2 overall alignment)2.66 / 5 ✎█▄·▄██▄▄█▄▄▄ beats 3/14easy · avg 3.83 / 5▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 94%at its level

$ where to run it

Other ways to run it

  1. Run it as published · needs ~3.6 GB, NVIDIA only · from huggingface.co/latent-consistency (official)
    uv run --with diffusers --with transformers --with accelerate --with torch python -c "import torch; from diffusers import UNet2DConditionModel, DiffusionPipeline, LCMScheduler; u=UNet2DConditionModel.from_pretrained('latent-consistency/lcm-ssd-1b', torch_dtype=torch.float16, variant='fp16'); p=DiffusionPipeline.from_pretrained('segmind/SSD-1B', unet=u, torch_dtype=torch.float16, variant='fp16'); p.scheduler=LCMScheduler.from_config(p.scheduler.config); p.to('cuda'); p('a cat holding a sign', num_inference_steps=4, guidance_scale=1.0).images[0].save('out.png')"

Official weights and documentation: huggingface.co/latent-consistency ↗

$ 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= 32.1

$ 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