Papers › Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free

Token Pruning for Caching Better: 9 Times Acceleration on Stable Diffusion for Free

31 Dec 2024arXiv:2501.00375archive 2025-07-28

Evelyn Zhang, Bang Xiao, Jiayi Tang, Qianli Ma, Chang Zou, Xuefei Ning, Xuming Hu, Linfeng Zhang

Stable Diffusion has achieved remarkable success in the field of text-to-image generation, with its powerful generative capabilities and diverse generation results making a lasting impact. However, its iterative denoising introduces high computational costs and slows generation speed, limiting broader adoption. The community has made numerous efforts to reduce this computational burden, with methods like feature caching attracting attention due to their effectiveness and simplicity. Nonetheless, simply reusing features computed at previous timesteps causes the features across adjacent timesteps to become similar, reducing the dynamics of features over time and ultimately compromising the quality of generated images. In this paper, we introduce a dynamics-aware token pruning (DaTo) approach that addresses the limitations of feature caching. DaTo selectively prunes tokens with lower dynamics, allowing only high-dynamic tokens to participate in self-attention layers, thereby extending feature dynamics across timesteps. DaTo combines feature caching with token pruning in a training-free manner, achieving both temporal and token-wise information reuse. Applied to Stable Diffusion on the ImageNet, our approach delivered a 9× speedup while reducing FID by 0.33, indicating enhanced image quality. On the COCO-30k, we observed a 7× acceleration coupled with a notable FID reduction of 2.17.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

EvelynZhang-epiclab/DaTo officialmentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DenoisingImage GenerationText to Image GenerationText-to-Image Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionDiffusionPruningSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections