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.
Generative adversarial networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
REJECT 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.