A token-pruning cache method cuts diffusion model computation by roughly half while keeping image quality, using noise magnitude, spatial clustering, and selection balance.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CAT Pruning: Cluster-Aware Token Pruning For Text-to-Image Diffusion Models
A token-pruning cache method cuts diffusion model computation by roughly half while keeping image quality, using noise magnitude, spatial clustering, and selection balance.