Text-to-Image
Diffusers

Sourced from https://civitai.com/models/2064593/flux-scfm-distilled-lora?modelVersionId=2336250

https://shortcutfm.github.io/

https://arxiv.org/abs/2510.17858

Shortcutting Pretrained Flow Matching Diffusion Models.

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.

Downloads last month
30
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for rockerBOO/Flux-SCFM-Distilled-LoRA

Finetuned
(508)
this model