cs.CVNov 19, 2026

Posterior Matching Distillation

Authors: Hidir Yesiltepe, Julius Berner, Arash Vahdat, Pinar Yanardag

Organizations: Virginia Tech · NVIDIA

Abstract

Diffusion distillation accelerates image and video generation by compressing a pretrained teacher's iterative sampling process into a few network evaluations. Distribution-based methods achieve this by matching the student's output distribution to the teacher's. This matching is often driven by reverse-KL objectives, whose mode-seeking bias favors dominant teacher modes at the expense of diversity across samples. We introduce Posterior Matching Distillation (PMD), a new member of the distribution-based distillation family that combines mode-covering posterior sampling with any-step generation. At zero population loss, PMD recovers the teacher's full posterior of clean images at each trained noise level. Its stochastic student supports any-step sampling budgets within the trained timestep grid without further training. To learn these posteriors, PMD matches exponentially reweighted averages of student samples conditioned on a fixed noisy state to corresponding teacher posterior means. Under Gaussian corruption, exponentially tilted posterior mean is a single teacher evaluation at a shifted input. We prove that, matching tilted means over an open neighborhood uniquely identifies the full posterior. PMD thus supervises the entire conditional distribution through a family of mean constraints, without any auxiliary student-score network. Experiments on SDXL and FLUX.2 [klein] 4B demonstrate that PMD achieves the best FID among 4-step methods on both models, while maintaining competitive or leading performance across prompt-alignment and perceptual-quality metrics.

Figures & tables

Explore similar work

CardsList
  1. DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation

    Oct 1, 2026Zhengming Yu, Junkun Yuan, Haotian Yang +8Diffusion Model DistillationFew-Step Diffusion Sampling

  2. Consistent Distribution Matching for Data-Free Diffusion Distillation

    Oct 6, 2026Yuxiang Fu, Qi Yan, Zike Wu +4Diffusion Model DistillationDiffusion Model Inference Acceleration

  3. Teacher-Feature Drifting: One-Step Diffusion Distillation with Pretrained Diffusion Representations

    May 8, 2026Yuan Zhang, Chenyi Li, Guoqing Ma +7Diffusion Model DistillationDiffusion Sampling