Pith. sign in

REVIEW 9 cited by

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

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2301.11093 v2 pith:UGOIEISS submitted 2023-01-26 cs.CV cs.LGstat.ML

Emiel Hoogeboom , Jonathan Heek , Tim Salimans This is my paper · ORCID
classification cs.CVcs.LGstat.ML
keywords diffusionhighresolutionimagesapproachesmodelssimplearchitecture
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. WaiT for the Signal: Simple Frequency-Aware Flow-Matching

    cs.CV 2026-07 conditional novelty 6.0 of 10

    WaiT delays high-frequency wavelet bands in flow-matching image generation until coarse structure emerges, improving quality and cutting compute, with a reported SOTA FID of 1.30 on ImageNet 512.

  2. FREPix: Frequency-Heterogeneous Flow Matching for Pixel-Space Image Generation

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    FREPix generates images by transporting low- and high-frequency wavelet components along separate schedules, reaching 1.91 FID on ImageNet 256×256.

  3. Guidance in the Frequency Domain Enables High-Fidelity Sampling at Low CFG Scales

    cs.LG 2025-06 conditional novelty 6.0 of 10

    By boosting high-frequency guidance while keeping low-frequency guidance modest, frequency-decoupled guidance improves image quality and diversity metrics across several diffusion models.

  4. InpDiffusion: Image Inpainting Localization via Conditional Diffusion Models

    cs.CV 2025-01 conditional novelty 6.0 of 10

    InpDiffusion treats image inpainting localization as a conditional mask-generation task with a diffusion model, using edge supervision to refine boundaries, and reports state-of-the-art AUC on Inpaint32K, DID, AutoSpl...

  5. INRFlow: Flow Matching for INRs in Ambient Space

    cs.LG 2024-12 conditional novelty 6.0 of 10

    A domain-agnostic PerceiverIO-style transformer, trained with a point-wise flow-matching loss in ambient space, generates competitive images, point clouds, and protein structures without a separate data compressor.

  6. Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet Encodings

    cs.CV 2024-11 conditional novelty 6.0 of 10

    Wavelet Latent Diffusion (WaLa) shrinks 3D shapes to 6,912-variable latent codes and trains billion-parameter diffusion models that generate 256^3 geometry in 2-4 seconds, claiming state-of-the-art results.

  7. Spatio-Temporal Conditional Diffusion Models for Forecasting Future Multiple Sclerosis Lesion Masks Conditioned on Treatments

    eess.IV 2025-08 conditional novelty 5.0 of 10

    A treatment-conditioned diffusion model generates future multiple sclerosis lesion masks from baseline MRI and better predicts lesion activity than population-level baselines.

  8. Conditional Diffusion Models are Medical Image Classifiers that Provide Explainability and Uncertainty for Free

    cs.CV 2025-02 conditional novelty 4.0 of 10

    Conditional diffusion models can classify medical images by comparing reconstruction errors, and the per-noise-level majority vote also yields explanation and uncertainty byproducts.

  9. Video Is Worth a Thousand Images: Exploring the Latest Trends in Long Video Generation

    cs.CV 2024-12 conditional novelty 3.0 of 10

    A survey of long video generation that groups methods into frame-by-frame, planned-segment, and all-at-once approaches, but is weakened by inconsistent data tables.

Pith tools