Papers › Simple diffusion: End-to-end diffusion for high resolution images

Simple diffusion: End-to-end diffusion for high resolution images

26 Jan 2023arXiv:2301.11093archive 2025-07-28

Emiel Hoogeboom, Jonathan Heek, Tim Salimans

Currently, applying diffusion models in pixel space of high resolution images is difficult. Instead, existing approaches focus on diffusion in lower dimensional spaces (latent diffusion), or have multiple super-resolution levels of generation referred to as cascades. The downside is that these approaches add additional complexity to the diffusion framework. This paper aims to improve denoising diffusion for high resolution images while keeping the model as simple as possible. The paper is centered around the research question: How can one train a standard denoising diffusion models on high resolution images, and still obtain performance comparable to these alternate approaches? The four main findings are: 1) the noise schedule should be adjusted for high resolution images, 2) It is sufficient to scale only a particular part of the architecture, 3) dropout should be added at specific locations in the architecture, and 4) downsampling is an effective strategy to avoid high resolution feature maps. Combining these simple yet effective techniques, we achieve state-of-the-art on image generation among diffusion models without sampling modifiers on ImageNet.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

fashn-AI/tryondiffusion mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Conditional Image GenerationDenoisingImage GenerationSuper-ResolutionText-to-Image GenerationVocal Bursts Intensity Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Conditional Image Generation ImageNet 128x128 simple diffusion (U-Net) FID 2.88 #4 of 22 Archive leaderboard report
Conditional Image Generation ImageNet 128x128 simple diffusion (U-Net) Inception score 137.3 #4 of 22 Archive leaderboard report
Conditional Image Generation ImageNet 128x128 simple diffusion (U-ViT, L) FID 3.23 #6 of 22 Archive leaderboard report
Conditional Image Generation ImageNet 128x128 simple diffusion (U-ViT, L) Inception score 171.9 #6 of 22 Archive leaderboard report
Image Generation ImageNet 256x256 simple diffusion (U-Net) FID 3.71 #75 of 94 Archive leaderboard report
Image Generation ImageNet 256x256 simple diffusion (U-ViT, L) FID 3.75 #76 of 94 Archive leaderboard report
Image Generation ImageNet 512x512 simple diffusion (U-Net) FID 4.28 #48 of 52 Archive leaderboard report
Image Generation ImageNet 512x512 simple diffusion (U-Net) Inception score 171 #48 of 52 Archive leaderboard report
Image Generation ImageNet 512x512 simple diffusion (U-ViT, L) FID 4.53 #50 of 52 Archive leaderboard report
Image Generation ImageNet 512x512 simple diffusion (U-ViT, L) Inception score 205.3 #50 of 52 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) simple diffusion (U-ViT) FID 8.3 #22 of 69 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

DiffusionDropout

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections