Metraipolis › archive › dc_a0711ea21348
Z-Cache: Accelerating Diffusion Transformers via Self-Reflection — arXiv:2611.01846
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.01846
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:54:45.783Z
- SHA-256 of the archived text
7f9ad33660254773da5868e31e51828513834835be5a686de4611a1730d50a38- Stable URL of this page
https://metraipolis.com/documento/dc_a0711ea21348
How to cite
Z-Cache: Accelerating Diffusion Transformers via Self-Reflection — arXiv:2611.01846 — arXiv (en), https://arxiv.org/abs/2611.01846 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a0711ea21348 (Metraipolis archive dc_a0711ea21348, sha256 7f9ad33660254773da5868e31e51828513834835be5a686de4611a1730d50a38)
BibTeX
@misc{dca0711ea21348,
title = {Z-Cache: Accelerating Diffusion Transformers via Self-Reflection — arXiv:2611.01846},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.01846},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a0711ea21348; sha256 7f9ad33660254773da5868e31e51828513834835be5a686de4611a1730d50a38},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01846. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2611.01846 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-03T18:16:52.960Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).