AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

DiP: Taming Diffusion Models in Pixel Space

Zhennan Chen, Junwei Zhu, Xu Chen, Jiangning Zhang, Xiaobin Hu, Hanzhen Zhao, Chengjie Wang, Jian Yang, Ying Tai

CVPR 2026 · Image generation › Autoregressive and latent generation · approach: High-resolution diffusion synthesis · 40 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 a conv U-Net Patch Detailer Head to the DiT backbone (ablation)DiP (DiT, patch 16) · ImageNet 256x256FID: 5.28 -> 2.16Improved
deepen DiT-only from 26 to 32 layers instead of adding head (ablation)DiT-only · ImageNet 256x256FID: 5.28 -> 4.91Improved
widen DiT-only hidden dim to 1536 (ablation)DiT-only · ImageNet 256x256FID: 5.28 -> 2.83Improved
use standard MLP as the patch head (ablation)Patch Detailer Head · ImageNet 256x256FID: 2.16 -> 6.92Hurt
use intra-patch attention instead of conv U-Net head (ablation)Patch Detailer Head · ImageNet 256x256FID: 2.16 -> 2.98Hurt
use coordinate-based MLP instead of conv U-Net head (ablation)Patch Detailer Head · ImageNet 256x256FID: 2.16 -> 2.20Hurt
place head intermediately or hybrid rather than post-hoc (ablation)Patch Detailer Head placement · ImageNet 256x256FIDHurt
train in pixel space with DiP rather than latent DiT-XLDiP-XL/16 · ImageNet 512x512FID: 3.04 -> 2.31Improved
increase head depth (down/up stages) (ablation)Patch Detailer Head · ImageNet 256x256FIDImproved
increase head width (ablation)Patch Detailer Head · ImageNet 256x256FIDNo clear effect

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