CivArchive
    SDXL Turbo - SDXL Turbo Pruned
    Preview 4009722
    Preview 4040344
    Preview 4128644
    Preview 4169863
    Preview 4169867
    Preview 4169865
    Preview 4168752
    Preview 4168754
    Preview 4168753
    Preview 4169869
    Preview 4169968
    Preview 4348787
    Preview 4348786
    Preview 4348789
    Preview 4348788
    Preview 4752096

    SDXL-Turbo is a distilled version of SDXL 1.0, trained for real-time synthesis. SDXL-Turbo is based on a novel training method called Adversarial Diffusion Distillation (ADD) (see the technical report), which allows sampling large-scale foundational image diffusion models in 1 to 4 steps at high image quality. This approach uses score distillation to leverage large-scale off-the-shelf image diffusion models as a teacher signal and combines this with an adversarial loss to ensure high image fidelity even in the low-step regime of one or two sampling steps.

    Developed by: Stability AI

    Description