cs.CVNov 12, 2026

eDMD: Endpoint Distribution Matching for Few-Step Diffusion Distillation

Authors: Tong Zhao, Xianfang Zeng, Yucheng Han, Ruoyu Wang, Mingkun Lei, Gang Yu, Chi Zhang

Organizations: Zhejiang University · AGI Lab, Westlake University · StepFun

Abstract

Distribution matching distillation (DMD) has emerged as a leading paradigm for distilling diffusion models into few-step students, where an auxiliary fake score model tracks the student's distribution and the discrepancy between the teacher and fake predictions drives the student toward the teacher. In multi-step distillation, although only the student's final output is delivered, existing methods train the fake model on intermediate states or across all denoising steps. Consequently, the student's update signal becomes entangled with intermediate distributions, which can distort the matching direction and remain nonzero even after the student's final outputs already match the teacher distribution. To resolve this mismatch, we propose Endpoint Distribution Matching Distillation (eDMD), which trains a single shared fake model exclusively on the student's final outputs and uses it to correct every denoising step. Our theoretical analysis proves that this endpoint reference guarantees that the distribution matching term vanishes if and only if the student's final output distribution matches the teacher's, regardless of intermediate distributions. Beyond the fake reference, we further strengthen teacher supervision through a precise teacher (PT) that replaces single-step guided predictions with short multi-step trajectories on the final noise interval, paired with a calibrated query density for intermediate steps. Experiments on SD3-Medium, FLUX.2-klein (4B and 9B), and Qwen-Image-2.1 demonstrate that eDMD consistently outperforms existing distribution matching methods for 4-step generation.

Figures & tables

Appendix figures & tables17 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Disagreement-Aware Distribution Matching Distillation for Few-Step Diffusion Models

    Nov 9, 2026Zikai Zhou, Zhengpeng Xie, Shitong Shao +4Diffusion Model DistillationDistribution Matching Distillation

  2. Continuous-Time Distribution Matching for Few-Step Diffusion Distillation

    May 7, 2026Tao Liu, Hao Yan, Mengting Chen +8Diffusion DistillationFew-Step Diffusion Sampling