Morse accelerates pretrained diffusion models by interleaving jump-sampling steps of the original model with a faster learned residual-correction model, reporting lossless average speedups of 1.78x to 3.31x.
Following the popular evaluation protocol, we evaluate the text-to-image diffusion models under zero-shot text-to-image generation on the MS-COCO 2014 validation set (Lin et al.,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.GR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Morse: Dual-Sampling for Lossless Acceleration of Diffusion Models
Morse accelerates pretrained diffusion models by interleaving jump-sampling steps of the original model with a faster learned residual-correction model, reporting lossless average speedups of 1.78x to 3.31x.