CacheScope: Exact-Compute Allocation for Training-Free Diffusion Acceleration
Training-free feature reuse accelerates diffusion transformer inference by replacing full denoising computation at selected steps with cached approximations. Existing methods mainly improve the reconstruction of skipped features, but we find that once a stable first-order reconstructor is used, increasing reconstructio...
Qinhan Lyu, Jusheng Zhang, Zhixing Zhang et al.
· 0 citations