2025
Token Pruning for Caching Better: 9$\times$ Acceleration on Stable Diffusion without Training
Evelyn Zhang*, Bang Xiao*, Fufu Yu, Jiayi Tang, Chang Zou, Ke Yan, Shouhong Ding, Qianli Ma, Fei Ren, Linfeng Zhang# (* equal contribution, # corresponding author)
Submitted to ICCV 2025
Based on token prune and layer cache technology, we present a new Stable Diffusion acceleration method named dynamics-aware token pruning (DaTo). In the COCO-30k, we observed a 7$\times$ acceleration coupled with a notable FID reduction of 2.17.
Token Pruning for Caching Better: 9$\times$ Acceleration on Stable Diffusion without Training
Evelyn Zhang*, Bang Xiao*, Fufu Yu, Jiayi Tang, Chang Zou, Ke Yan, Shouhong Ding, Qianli Ma, Fei Ren, Linfeng Zhang# (* equal contribution, # corresponding author)
Submitted to ICCV 2025
Based on token prune and layer cache technology, we present a new Stable Diffusion acceleration method named dynamics-aware token pruning (DaTo). In the COCO-30k, we observed a 7$\times$ acceleration coupled with a notable FID reduction of 2.17.