README.md

---
license: apache-2.0
pipeline_tag: text-to-image
datasets:
- CaptionEmporium/midjourney-niji-1m-llavanext
---

# Simple Diffusion XS

*XS Size, Excess Quality*
![promo](media/girl.jpg)

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](https://huggingface.co/zer0int/CLIP-KO-LITE-TypoAttack-Attn-Dropout-ViT-L-14)
- Qwen3.5: [Qwen3.5-2B](https://huggingface.co/Qwen/Qwen3.5-2B) 
- VAE:     32ch8x(Flux2)

### Random samples
![promo](media/result_grid.jpg)

### 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)
```
### Train:

```
apt update
apt install git-lfs
git config --global credential.helper store
git clone https://huggingface.co/AiArtLab/sdxs-1b
cd sdxs-1b
pip install -r requirements.txt -U
mkdir datasets
cd datasets
hf download babkasotona/ds1234_1280  --repo-type dataset --local-dir ds1234_1280
cd ..
nohup accelerate launch train.py &
```

### Model Limitations:
- Limited concept coverage due to the small dataset (1kk).

## Acknowledgments
- **[Stan](https://t.me/Stangle)** — Key investor. Thank you for believing in us when others called it madness.
- **Captainsaturnus**
- **Love. Death. Transformers.**
- **TOPAPEC**

## Datasets
- **[CaptionEmporium](https://huggingface.co/CaptionEmporium)**

## Donations

 - Rubles: [For users from Russia](https://www.tbank.ru/cf/90ensBQqpJj)
 - DOGE: DEw2DR8C7BnF8GgcrfTzUjSnGkuMeJhg83
 - BTC: 3JHv9Hb8kEW8zMAccdgCdZGfrHeMhH1rpN
 - Crypto: [https://nowpayments.io/donation/sdxs](https://nowpayments.io/donation/sdxs)

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

 - telegram [recoilme](https://t.me/recoilme) *prefered way
 - mail at aiartlab.org (slow response)

mail at aiartlab.org (slow response)

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