Instructions to use recoilme/sdxs with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use recoilme/sdxs with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("recoilme/sdxs", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Commit History
-
SDXS 1.996B: looped single-stream DiT (6 in + 8 mid x2 + 6 out, 28 passes)
- teacher-free flow-matching training (train.py), distill kept as train_distill.py - native FLUX.2-klein text format (Qwen3.5-2B [2,12,22] -> 6144) - asymmetric VAE 8x/16x, prompt-consistent pipeline (pipeline_sdxs.py)ef2542c