English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Diffusion models have found widespread adoption in various areas. However,their sampling process is slow because it requires hundreds to thousands ofnetwork evaluations to emulate a continuous process defined by differentialequations. In this work, we use neural operators, an efficient method to solvethe probability flow differential equations, to accelerate the sampling processof diffusion models. Compared to other fast sampling methods that have asequential nature, we are the first to propose a parallel decoding method thatgenerates images with only one model forward pass. We propose diffusion modelsampling with neural operator (DSNO) that maps the initial condition, i.e.,Gaussian distribution, to the continuous-time solution trajectory of thereverse diffusion process. To model the temporal correlations along thetrajectory, we introduce temporal convolution layers that are parameterized inthe Fourier space into the given diffusion model backbone. We show our methodachieves state-of-the-art FID of 3.78 for CIFAR-10 and 7.83 for ImageNet-64 inthe one-model-evaluation setting.

Fast Sampling of Diffusion Models via Operator Learning