AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

PixelDiT: Pixel Diffusion Transformers for Image Generation

Yongsheng Yu, Wei Xiong, Weili Nie, Yichen Sheng, Shiqiu Liu, Jiebo Luo

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 55 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
add RoPE and RMSNorm (ablation)Vanilla DiT/16 · ImageNet 256x256 ablation (80 epochs)gFID: 9.84 -> 8.53Improved
add dual-level pathway with pixel token compaction (ablation)Vanilla DiT/16 · ImageNet 256x256 ablation (80 epochs)gFID: 8.53 -> 3.50Improved
add pixel-wise AdaLN (ablation)PixelDiT-XL · ImageNet 256x256 ablation (80 epochs)gFID: 3.50 -> 2.36Improved
add pixel token compaction to dual-level design (ablation)PixelDiT-XL · ImageNet 256x256 computeGFLOPs: 82247 -> 311Improved
add self-attention in the pixel-level pathway (ablation)PixelDiT-XL · ImageNet 256x256 ablation (80 epochs)gFID: 2.56 -> 2.36Improved
add representation alignment (REPA) (ablation)PixelDiT-XL · ImageNet 256x256 ablation (80 epochs)gFID: 6.58 -> 2.36Improved
use compaction to 1x sequence length instead of 4x (ablation)PixelDiT · ImageNet 256x256 ablation (300K iterations)gFID: 2.43 -> 2.34Improved
use patch size 16 instead of 32 (ablation)PixelDiT · ImageNet 512x512 ablation (120 epochs)FID: 3.78 -> 2.23Improved
use patch size 16 instead of 32 (ablation)PixelDiT-B · ImageNet 256x256 ablation (200K iterations)gFID: 48.5 -> 15.1Improved
use patch size 8 instead of 16 (ablation)PixelDiT-L · ImageNet 256x256 ablation (300K iterations)gFID: 2.72 -> 2.15Improved
use patch size 8 instead of 16 (ablation)PixelDiT-XL · ImageNet 256x256 ablationgFIDNo clear effect
scale model from B/16 to XL/16 (ablation)PixelDiT · ImageNet 256x256 ablation (200K iterations)gFID: 15.1 -> 2.95Improved

Later papers that compared with this method

2 later accepted papers report PixelDiT as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

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