flux-scfm

Prompt

-

Model description

This lora checkpoint allows you to generate images within 3-8 steps by applying the weight as a LoRA on the FLUX series checkpoints.

Recommended settings: lora strength 1.0-1.75, cfg >=3.5. Lower steps generally require higher strength.

For more details, please do not hesitate to check our paper: Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch and the GitHub Repo.

For SD3.5, the only recommended negative prompt is null (i.e., an empty string ""), since the checkpoint was trained exclusively with this setting.

Trigger words

Perhaps you can try words like ultrarealistic to get better results.

Download model

Download them in the Files & versions tab.