Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch
Paper • 2510.17858 • Published • 1
How to use rockerBOO/Flux-SCFM-Distilled-LoRA with Diffusers:
pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("rockerBOO/Flux-SCFM-Distilled-LoRA", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Sourced from https://civitai.com/models/2064593/flux-scfm-distilled-lora?modelVersionId=2336250
https://arxiv.org/abs/2510.17858
This model allows you to generate images within 3-8 steps by applying the weight as a LoRA on the FLUX series checkpoint.
It has been accepted for presentation at NeurIPS 2025.
For further technical details, please refer to our paper and the associated project.
Recommended settings: lora strength 1.0-1.75, cfg >=4.5. Lower steps require higher strength.
Base model
black-forest-labs/FLUX.1-dev