Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervals

Xiangyu Fan, Zesong Qiu, Zhuguanyu Wu, Fanzhou Wang, Zhiqian Lin, Tianxiang Ren, Dahua Lin, Ruihao Gong, Lei Yang

Keywords: diffusion models, distribution matching, distill, score matching

TL;DR: improve object motion speed in video generation

Abstract:

Distribution Matching Distillation (DMD) distills score-based generative models into efficient one-step generators,
without requiring a one-to-one correspondence with the sampling trajectories of their teachers.
However, limited model capacity causes one-step distilled models underperform on complex generative tasks, e.g.,
synthesizing intricate object motions in text-to-video generation.
Directly extending DMD to multi-step distillation increases memory usage and computational depth, leading to instability and reduced efficiency.
While prior works propose stochastic gradient truncation as a potential solution,
we observe that it substantially reduces the generation diversity of multi-step distilled models,
bringing it down to the level of their one-step counterparts.
To address these limitations, we propose **Phased DMD**, a multi-step distillation framework that bridges the idea of phase-wise distillation with Mixture-of-Experts (MoE), reducing learning difficulty while enhancing model capacity.
Phased DMD is built upon two key ideas: **progressive distribution matching** and **score matching within subintervals**.
First, our model divides the SNR range into subintervals, progressively refining the model to higher SNR levels, to better capture complex distributions.
Next, to ensure the training objective within each subinterval is accurate, we have conducted rigorous mathematical derivations.
We validate Phased DMD by distilling state-of-the-art (SOTA) image and video generation models, including Qwen-Image (20B parameters) and Wan2.2 (28B parameters).
Experimental results demonstrate that Phased DMD preserves output diversity better than DMD while retaining key generative capabilities.
We will release our code and models.

Primary Area: generative models

Submission Number: 10813