cs.CVNov 1, 2026

Z-Cache: Accelerating Diffusion Transformers via Self-Reflection

Authors: Zegang Cheng, Zhikai Wang, Jiacheng Liu, Xiaobing Tu, Chang Zou, Junjie Chen, Yue Ma, Zhiyuan Ma, 

Organizations: Shanghai Jiao Tong University · Southern University of Science and Technology · Alibaba Cloud · Huazhong University of Science and Technology

Abstract

Diffusion transformers have become the most powerful models for visual generation, but still suffer from massive computation costs. To solve this problem, feature caching has been proposed to cache the features of diffusion models in the previous computation steps and then reuse them in the following caching steps, which brings significant acceleration but also degradation in generation quality. To address this problem, this paper proposes Z-cache as a feature caching method that can maintain high-quality generation through self-reflection. Concretely, we observe that the error from feature caching tends to be sharply reduced after each full computation. Based on this observation, Z-Cache is designed to first predict the features in the future caching steps and then perform a full computation. After that, Z-Cache returns to the caching steps and re-predicts them based on the previous and the current computation steps, which brings correction in features. Experiments demonstrate that with Z-Cache, diffusion transformers achieve comparable generation quality to the original model but with faster inference speed, for instance, 6.22X acceleration on FLUX-dev for text-to-image generation. Our code is released on GitHub.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. IdealCache: Rethinking Cache Scheduling in Diffusion Transformers via Ideal Trajectories

    Nov 7, 2026Shang Xue, Li Zhu, Ping ChenDiffusion Model CachingDiffusion Model Acceleration

  2. LearniBridge: Learnable Calibration of Feature Caching for Diffusion Models Acceleration

    Jun 25, 2026Xuyue Huang, Zhe Chen, Wang Shen +1Video Diffusion ModelsDiffusion Transformer