We propose explicit and interpretable one-step generation framework that retains the advantages of traditional diffusion models, such as access to intermediate states and fine-grained control, while enabling fast sampling.

We propose the Koopman Distillation Model (KDM), a novel offline distillation method for diffusion models that leverages Koopman theory to enable single-step generation with strong semantic consistency and state-of-the-art FID performance.