A diffusion model can be made faster by alternately optimizing the noise schedule and finetuning the denoiser, yielding lower FID at small step counts on three datasets.
Learning fast samplers for diffusion models by differentiating through sample quality
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.CV 1years
2024 1verdicts
REJECT 1roles
background 1polarities
contest 1representative citing papers
citing papers explorer
-
Optimizing Few-Step Sampler for Diffusion Probabilistic Model
A diffusion model can be made faster by alternately optimizing the noise schedule and finetuning the denoiser, yielding lower FID at small step counts on three datasets.