AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

DDT: Decoupled Diffusion Transformer

Shuai Wang, Zhi Tian, Weilin Huang, Limin Wang

CVPR 2026 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 99 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
decouple into condition encoder and velocity decoderImproved-REPA-B/2 · ImageNet 256x256 (400K steps, w/o CFG)FID: 19.1 -> 16.32Improved
decouple into condition encoder and velocity decoderImproved-REPA-XL/2 · ImageNet 256x256 (400K steps, w/o CFG)FID: 8.14 -> 6.62Improved
increase encoder share of layers (8En4De for Base) (ablation)DDT-B/2 · ImageNet 256x256 (DDT-B/2, 400K steps)FID: best of 4En8De, 6En6De, 8En4De, 10En2DeImproved
use aggressive encoder-decoder ratio 20En4De for Large (ablation)DDT-L/2 · ImageNet 256x256 (DDT-L/2, 400K steps)FID: best of 10En14De to 20En4DeImproved
replace decoder attention with 3x3 conv (ablation)DDT-B/2 decoder · ImageNet 256x256 (DDT-B/2, 400K steps)FID: 16.32 -> 16.96No clear effect
replace decoder attention with MLP only (ablation)DDT-B/2 decoder · ImageNet 256x256 (DDT-B/2, 400K steps)FID: 16.32 -> 24.13Hurt
add statistic dynamic programming sharing instead of uniform sharing at 3.0x (ablation)DDT-XL/2 · ImageNet 256x256 with CFGFID: 1.42 -> 1.40Improved
share self-condition across steps for 2.6x speedup (uniform) (ablation)DDT-XL/2 · ImageNet 256x256 with CFGFID: 1.31 -> 1.36No clear effect
add improved-baseline techniques (SwiGLU, RoPE, RMSNorm, lognorm) to REPA-B/2 (ablation)REPA-B/2 · ImageNet 256x256 (400K steps, w/o CFG)FID: 24.4 -> 19.1Improved
add improved-baseline techniques to REPA-XL/2 (ablation)REPA-XL/2 · ImageNet 256x256 (400K steps, w/o CFG)FID: 7.9 -> 8.14No clear effect
DDT-XL/2 vs baseline training costDDT-XL/2 · Training speed XL/2s/it: 0.25s/it -> 0.26s/itNo 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