Skip to content
NewA calmer, faster ZeroHour

eDMD matches endpoints for few-step diffusion distillation

Original title: eDMD: Endpoint Distribution Matching for Few-Step Diffusion Distillation

Hugging Face daily papersby Tong Zhao, Xianfang Zeng, Yucheng Han ()1 min read
AI summary · x-ai/grok-4.7Summaries by Vani AI

One shared fake model is trained only on final student outputs and improves 4-step generation.

Endpoint Distribution Matching Distillation trains a single shared fake score model exclusively on a student's final outputs and uses it to correct every denoising step. The authors prove the matching term vanishes if and only if the student's final distribution matches the teacher's, regardless of intermediate states. A precise teacher replaces single-step guided predictions with short multi-step trajectories on the final noise interval. Experiments on SD3-Medium, FLUX.2-klein (4B and 9B) and Qwen-Image-2.1 report better 4-step results than existing distribution matching methods.

Key facts
  • Existing methods train the fake model on intermediate states or all steps.
  • eDMD uses one shared fake model on final student outputs only.
  • The precise teacher uses short trajectories on the final noise interval.
  • Evaluated models include SD3-Medium, FLUX.2-klein and Qwen-Image-2.1.
  • Reported gains are for 4-step generation.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

1 min read at huggingface.co

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.

Hugging Face daily papers

By Tong Zhao, Xianfang Zeng, Yucheng Han · huggingface.co

Read the full article at Hugging Face daily papers

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.