Pixel-Space Diffusion Models

Overview

Pixel-space diffusion models learn to generate or reconstruct images directly in RGB, aiming to preserve details that image tokenizers or autoencoders can discard. Common approaches include Diffusion Transformers and flow matching, with multiscale or frequency-aware denoising, semantic representation guidance, and token compression or distillation to reduce computation. On benchmarks such as ImageNet at 256 or 512 pixels and text-to-image evaluations such as GenEval, pixel-space models now reach competitive quality, and the same techniques are being applied to restoration, geometry, and inverse problems. The main tension is that raw pixels demand more computation and can make training slower than latent-space methods, while eliminating the latent bottleneck does not always improve downstream results.

Latest papers

CardsList

65 papers9 papers in the last four weeks, down 50% on the four weeks before. 0.1% of all new papers.

  1. WiT: Waypoint Diffusion Transformers for Alleviating Trajectory Conflict in Pixel-Space Image Generation

    Mar 16, 2026Hainuo Wang, Mingjia Li, Xiaojie GuoFlow MatchingDiffusion Transformer

  2. Representation Alignment for Just Image Transformers is not Easier than You Think

    Mar 15, 2026Jaeyo Shin, Jiwook Kim, Hyunjung ShimDiffusion ModelsDiffusion Model Alignment

  3. Scale Space Diffusion

    Mar 9, 2026Soumik Mukhopadhyay, Prateksha Udhayanan, Abhinav ShrivastavaPixel-Space Diffusion ModelsDiffusion Model Acceleration

  4. SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization

    Oct 6, 2025Théophane Vallaeys, Jakob Verbeek, Matthieu CordImage TokenizationImage Reconstruction