AiArtLab/sdxs-1b

Simple Diffusion XS

XS Size, Excess Quality

At AiArtLab, we strive to create a free, compact and fast model that can be trained on consumer graphics cards.

• Unet: 1.5b parameters
• Clip: LongCLIP with 248 tokens
• Qwen3: Qwen3-VL-2B
• VAE: 32ch8x(Flux2)
• Speed: Sampling 100%|██████████| 40/40 [00:01<00:00, 30.72it/s]

Random samples

Example

import torch
from diffusers import DiffusionPipeline

device = "cuda" if torch.cuda.is_available() else "cpu"
dtype = torch.float16 if torch.cuda.is_available() else torch.float32

pipe_id = "AiArtLab/sdxs-1b"
pipe = DiffusionPipeline.from_pretrained(
    pipe_id,
    torch_dtype=dtype,
    trust_remote_code=True
).to(device)

prompt = "girl, smiling, red eyes, blue hair, white shirt"
negative_prompt="low quality"
image = pipe(
    prompt=prompt,
    negative_prompt = negative_prompt,
).images[0]

image.show(image)

Model Limitations:

• Limited concept coverage due to the small dataset (1kk).

Acknowledgments

• Stan — Key investor. Thank you for believing in us when others called it madness.
• Captainsaturnus
• Love. Death. Transformers.
• TOPAPEC

Datasets

• CaptionEmporium

Donations

• Rubles: For users from Russia
• DOGE: DEw2DR8C7BnF8GgcrfTzUjSnGkuMeJhg83
• BTC: 3JHv9Hb8kEW8zMAccdgCdZGfrHeMhH1rpN
• Crypto: https://nowpayments.io/donation/sdxs

Contacts

Please contact with us if you may provide some GPU's or money on training

• telegram recoilme *prefered way
• mail at aiartlab.org (slow response)

mail at aiartlab.org (slow response)

Citation

@misc{sdxs,
  title={Simple Diffusion XS},
  author={recoilme, muinez and AiArtLab Team},
  url={https://huggingface.co/AiArtLab/sdxs-1b},
  year={2026}
}