AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Just-in-Time: Training-Free Spatial Acceleration for Diffusion Transformers

Wenhao Sun, Ji Li, Zhaoqiang Liu

CVPR 2026 · Image generation › Fast diffusion sampling · approach: Training-free diffusion acceleration · 3 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
use JiT spatial acceleration (18 NFE) instead of the 50-NFE baselineFLUX.1-dev · Text-to-image (~4x tier)ImageReward: 1.004 -> 1.017Improved
use JiT instead of 7-NFE FLUX.1-dev at equal speedFLUX.1-dev · Text-to-image (~7x tier)ImageReward: 0.7474 -> 0.9746Improved
use JiT instead of RALU at ~7xFLUX.1-dev · Text-to-image (~7x tier)HPSv2.1: 29.71 -> 29.02Hurt
use JiT at 18 NFE instead of the 50-NFE baselineFLUX.1-dev · Text-to-image (~4x tier)HPSv2.1: 30.39 -> 29.77Hurt
use JiT instead of 7-NFE FLUX.1-dev in blind human comparisonsFLUX.1-dev · User studypreference for JiT (%): 93.1% preferenceImproved
add spatial approximation (interpolated velocity) for inactive tokens in SAG-ODE (ablation)JiT · AblationHPSv2.1: 24.18 -> 26.90Improved
add spatial approximation for inactive tokens in SAG-ODE (ablation)JiT · AblationT2I-CompBench: 0.3414 -> 0.3727Improved
use importance-guided token activation instead of static fixed grid (ablation)JiT · AblationHPSv2.1: 26.51 -> 26.90Improved
use noise-aware DMF target instead of naive interpolation (ablation)JiT · AblationHPSv2.1: 26.04 -> 26.90Improved
use noise-aware DMF target instead of naive interpolation (ablation)JiT · AblationT2I-CompBench: 0.3602 -> 0.3727Improved

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