SoftCache: Adaptive Step Size Caching for Diffusion Transformers

SoftCache introduces an adaptive step size caching mechanism for diffusion transformers, replacing hard binary caching with a soft approach that uses a headroom signal to determine how far cached steps advance. By allowing steps to jump beyond scheduled nodes and shrink as a refresh nears, SoftCache achieves significant speedups—between 3.5× and 6.9×—across image and video models such as FLUX, HunyuanVideo, and Wan2.1, outperforming all baselines on four fidelity metrics.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

• llms
• diffusion