AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Hi-DiT: Hybrid Latent-Pixel Diffusion Transformer for Image Generation

Yedong Shen, Yehao Li, Yingwei Pan, Yanyong Zhang, Ting Yao

ECCV 2026 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 0 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 parallel latent branch to pixel-stream baseline (ablation)Hi-DiT · ImageNet 256x256 (80-epoch ablation)FID: 3.38 -> 1.74Improved
replace MLP pixel predictor with hierarchical sub-pixel HF Pixel Predictor (ablation)Hi-DiT · ImageNet 256x256 (80-epoch ablation)FID: 1.74 -> 1.65Improved
set time-gating threshold tau to 0.3 instead of 0.7 (ablation)Hi-DiT · ImageNet 256x256 (80-epoch ablation)FID: 1.73 -> 1.65Improved
set time-gating threshold tau to 0.3 instead of 0.1 (ablation)Hi-DiT · ImageNet 256x256 (80-epoch ablation)FID: 1.75 -> 1.65Improved
add latent+pixel hybrid with time-gated injection to SiT latent diffusionSiT-XL · ImageNet 256x256 (w/ CFG)FID: 2.06 -> 1.06Improved
hybrid latent-pixel design without CFGSiT-XL · ImageNet 256x256 (w/o CFG)FID: 8.61 -> 1.66Improved
add hybrid latent-pixel design to U-ViT-S/2 for text-to-imageU-ViT-S/2 · MS-COCO 256x256 text-to-imageFID: 5.48 -> 5.15Improved
raise CFG scale from 2.4 to 3.0 (ablation)Hi-DiT · ImageNet 256x256 (w/ CFG)FID / IS: FID 1.06 -> 1.10, IS 296.6 -> 319.4Mixed
add pixel stream and pixel predictor on top of latent backboneSiT / VA-VAE · ImageNet 256x256 costinference time per image (s): 1.52 -> 1.67 (SiT); peak mem 32.90G -> 35.52GHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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