AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Distilling Diffusion Models into Conditional GANs

MinGuk Kang, Richard Zhang, Connelly Barnes, Sylvain Paris, Suha Kwak, Jaesik Park, Eli Shechtman, Jun-Yan Zhu, Taesung Park

ECCV 2024 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 48 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

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
replace MSE with E-LatentLPIPS as ODE distillation loss (ablation)ODE distillation · SD-CFG-3, COCO2014FID: 110.55 -> 22.95Improved
add ensembled augmentations to LatentLPIPS (ablation)ODE distillation · SD-CFG-3, COCO2014FID: 67.17 -> 22.95Improved
use E-LatentLPIPS in latent space instead of pixel LPIPS (ablation)ODE distillation · SD-CFG-3, COCO2014FID: 25.94 -> 22.95Improved
increase batch size from 256 to 2048 (ablation)ODE distillation with E-LatentLPIPS · SD-CFG-3, COCO2014FID: 22.95 -> 14.72Improved
add pre-trained diffusion discriminator instead of GigaGAN discriminator (ablation)Diffusion2GAN · SD-CFG-3, COCO2014FID-30k: 13.97 -> 12.04Improved
add single-sample R1 regularization (ablation)Diffusion2GAN discriminator · SD-CFG-3, COCO2014FID-30k: 11.97 -> 10.60Improved
add multi-scale in-and-out discriminator (ablation)Diffusion2GAN · SD-CFG-3, COCO2014FID-30k: 10.60 -> 9.58Improved
add mix-and-match augmentation (ablation)Diffusion2GAN · SD-CFG-3, COCO2014FID-30k: 9.58 -> 9.45Improved
add z-conditioning to the discriminator (ablation)Diffusion2GAN discriminator · SD-CFG-3, COCO2014FID-30k: 12.04 -> 11.97No clear effect
add conditional GAN training to ODE distillation (ablation)ODE distillation · COCO2014FID-30k: 15.94 -> 9.29Improved
use deterministic ODE pairs vs stochastic or re-wired pairs (ablation)ODE distillation · EDM CIFAR10, 50k pairsFID: FID over 200 -> 8.51Improved
scale up ODE pair dataset (ablation)ODE distillation (LPIPS) · CIFAR10FID-50k: 8.51 -> 3.16Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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