CivArchive
    ByteDance Hyper-FLUX Acceleration LoRA - Hyper-FLUX.1-dev-8steps
    Preview 26372625

    Hyper-SD is one of the new State-of-the-Art diffusion model acceleration techniques.

    For more information, please refer to https://huggingface.co/ByteDance/Hyper-SD.

    Description

    Our 8-steps and 16-steps FLUX.1-dev-related LoRAs are available now! We recommend LoRA scales around 0.125 that is adaptive with training and guidance scale could be kept on 3.5. Lower step LoRAs would be coming soon.

    LORA
    Flux.1 D

    Details

    Downloads
    1,722
    Platform
    CivitAI
    Platform Status
    Available
    Created
    8/27/2024
    Updated
    9/27/2025
    Deleted
    -