FlexCache compresses video latent caches and decouples object and background prompt lookups to accelerate text-to-video diffusion serving by 1.26x at 25% lower cost.
Stable video dif- fusion: Scaling latent video diffusion models to large datasets, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.MM 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
FlexCache: Flexible Approximate Cache System for Video Diffusion
FlexCache compresses video latent caches and decouples object and background prompt lookups to accelerate text-to-video diffusion serving by 1.26x at 25% lower cost.