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

Sampling from diffusion models can be treated as solving the correspondingordinary differential equations (ODEs), with the aim of obtaining an accuratesolution with as few number of function evaluations (NFE) as possible.Recently, various fast samplers utilizing higher-order ODE solvers have emergedand achieved better performance than the initial first-order one. However,these numerical methods inherently result in certain approximation errors,which significantly degrades sample quality with extremely small NFE (e.g.,around 5). In contrast, based on the geometric observation that each samplingtrajectory almost lies in a two-dimensional subspace embedded in the ambientspace, we propose Approximate MEan-Direction Solver (AMED-Solver) thateliminates truncation errors by directly learning the mean direction for fastdiffusion sampling. Besides, our method can be easily used as a plugin tofurther improve existing ODE-based samplers. Extensive experiments on imagesynthesis with the resolution ranging from 32 to 256 demonstrate theeffectiveness of our method. With only 5 NFE, we achieve 7.14 FID on CIFAR-10,13.75 FID on ImageNet 64$\times$64, and 12.79 FID on LSUN Bedroom. Our code isavailable at https://github.com/zhyzhouu/amed-solver.

Fast ODE-based Sampling for Diffusion Models in Around 5 Steps