AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

One-Step Diffusion Distillation via Deep Equilibrium Models

Zhengyang Geng, Ashwini Pokle, J Zico Kolter

NeurIPS 2023 · Image generation › Fast diffusion sampling · approach: Fast diffusion ODE solvers · 5 citations (OpenAlex)

This paper tried a common change: Larger batch size

increase batch size to 2×BS · CIFAR-10 unconditional · FID: 7.42 -> 6.91 Improved

What 785 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
distill directly from noise/image pairs with GET rather than use progressive distillationCIFAR-10 unconditional generation · CIFAR-10 unconditionalFID: 9.12 -> 6.91Improved
use GET instead of ViT-BaseCIFAR-10 unconditional generation · CIFAR-10 unconditionalFID: 11.49 -> 10.72Improved
use GET-Mini instead of ViT-BaseCIFAR-10 unconditional generation · CIFAR-10 unconditionaltraining speed: 4.83 iter/sec -> 5.79 iter/secImproved
use GET-Mini instead of ViT-BaseCIFAR-10 unconditional generation · CIFAR-10 unconditionaltraining memory per GPU: 10.1GB -> 9.2GBImproved
increase GET capacity from Tiny to Base (ablation)GET · CIFAR-10 unconditionalFID: 15.19 -> 7.42Improved
train GET-Tiny for 4× iterations (ablation)GET-Tiny · CIFAR-10 unconditionalFID: 15.19 -> 11.47Improved
increase batch size to 2×BS (ablation)GET-Base · CIFAR-10 unconditionalFID: 7.42 -> 6.91Improved
increase training data from 1M to 2M noise-image pairs (ablation)class-conditional GET-Base · CIFAR-10 class-conditionalFIDImproved
use additive class injection instead of AdaLN-Zero (ablation)class-conditional ViT-B · CIFAR-10 class-conditioning ablation, 200k iterationsFID: 17.19 -> 12.43Improved
add class conditioning through AdaLN-Zero (ablation)ViT-B · CIFAR-10 class-conditioning ablation, 200k iterationsFID: 15.20 -> 17.19Hurt
use GET instead of Guided DistillationCIFAR-10 class-conditional generation · CIFAR-10 class-conditionalFID: 7.34 -> 6.25Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy