
The Sub-path Linear Approximation Model (SLAM) accelerates diffusion models while maintaining high-quality image generation by treating the PF-ODE trajectory as a series of sub-paths and using sub-path linear ODEs to form a progressive and continuous error estimation along each sub-path.


coremsg

efficient-image-generation-with-sub-path-linear-approximation-model


Efficient Image Generation with Sub-path Linear Approximation Model


title_rewrite


FRDiff leverages the temporal redundancy inherent in diffusion models to significantly reduce computation overhead while maintaining output quality through feature reuse, score mixing, and automated hyperparameter tuning.


frdiff-accelerating-diffusion-models-through-feature-reuse


FRDiff: Accelerating Diffusion Models through Feature Reuse
