AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Adding Additional Control to One-Step Diffusion with Joint Distribution Matching

Yihong Luo, Tianyang Hu, Yifan Song, Jiacheng Sun, Zhenguo Li, Jing Tang

ICCV 2025 · Image generation › Fast diffusion sampling · approach: Distillation for few-step generation · 9 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
train one-step student with joint distribution matching instead of DI + standard ControlNetone-step SD 1.5 with control · controllable generation averageFID: 22.21 -> 14.58Improved
JDM one-step vs 50-step ControlNetJDM · controllable generation averageConsistency: 0.093 -> 0.071Improved
JDM one-step vs 50-step ControlNet on depth and super-resolutionJDM · Depth and 8x SRFID: 15.25 -> 16.24 (Depth); 11.93 -> 12.48 (SR)Hurt
train ControlNet via denoising loss on one-step generator (ablation)DI one-step generator · CannyFID: 13.07 -> 28.83Hurt
implicitly train ControlNet with original VSD loss (ablation)one-step student · CannyConsistency: 0.102 -> 0.151Hurt
use two-phase warm-up for shared one-step UNet (ablation)JDM · CannyConsistency: 0.122 -> 0.102Improved
model log p(c|x_t) with a consistency model (ablation)JDM · DepthFID: 18.56 -> 16.24Improved
use decoupled CFG from SD-v2.1 teacherJDM text-to-image · text-to-image SD-v1.5HPS average: 29.46 -> 29.75 (vs HFL)Improved
add human feedback learning jointly with one-step trainingJDM · text-to-image SD-v1.5HPS average: 26.35 -> 29.46 (vs Diff-Instruct)Improved
use log p(c|x_0) directly for HFL (ablation)JDM · human feedback learningvisual artifactsHurt

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