
KZ
Kun Zhou, Wenmian Yang, Zhensheng Wang, Weijia Jia
· 1 min read
ResearcharXiv cs.CV
Text Lives in the Guidance: Preventing Silent Text Rewriting in Cached Diffusion Transformers
arXiv:2611.25382v1 Announce Type: new
Abstract: Diffusion transformers (DiTs) now render long, legible text in images, and feature caching is a standard way to accelerate them. Caches are judged by image-level metrics, which do not check whether the rendered text is still correct. We find that caching silently rewrites this text. On Z-Image, TaylorSeer at 2.9x fewer FLOPs lowers word accuracy from 62% to 46%, while ImageReward and CLIP Score barely change. Sampling with fewer steps at the same compute keeps almost all of this text, so the loss comes from how the cache predicts the skipped steps. Decomposing the cache error along classifier-free guidance (CFG), we trace this loss mainly to the guidance term, the difference between the conditional and unconditional predictions, which caches extrapolate worst on text. Correcting the guidance inside the text alone recovers most of the lost text. We therefore propose GuideCache, which recomputes both CFG branches only on the tokens with the largest predicted guidance error, using the guidance terms that the cache already stores. At 2.4x fewer FLOPs, GuideCache restores full-compute prompt fidelity on Z-Image and Qwen-Image, and on Z-Image it renders text as well as or better than ToCa, TeaCache, and FasterCache while staying much closer to the full model's output. GuideCache works with caches of any order, and on top of fewer sampling steps it keeps more text than step reduction at a higher speedup. These results suggest that acceleration methods for text-rendering models should be evaluated on the text they render.
Original source
This story was published by arXiv cs.CV and written by Kun Zhou, Wenmian Yang, Zhensheng Wang, Weijia Jia. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


