Diffusion Model Distillation

Overview

Diffusion model distillation studies how to make models that generate images, video, audio, text, and other data through repeated denoising faster or smaller while retaining their capabilities. Common approaches train a student to match a teacher’s denoising trajectory or output distribution, progressively reduce sampling steps, or use consistency and flow-matching objectives; compression and guidance distillation can further reduce cost. Newer work also uses on-policy and self-distillation, where the student’s own generation paths guide training, and reward-based objectives to improve preference alignment. A central tension is reducing inference cost without losing diversity, fine detail, temporal consistency, or reliability, especially in very few-step and long-horizon generation.

Latest papers

213 papers31 papers in the last four weeks, down 24% on the four weeks before. 0.2% of all new papers.

May 30, 2025

DLM-One: Diffusion Language Models for One-Step Sequence Generation

This paper introduces DLM-One, a score-distillation-based framework for one-step sequence generation with continuous diffusion language models (DLMs). DLM-One eliminates iterative refinement by aligning the scores of a student model's outputs with the score function of a pretrained teacher DLM in the forward-diffused noisy space. We demonstrate that our framework is architecture-agnostic and robust across diverse continuous manifolds, including standard token embedding spaces and logit simplex spaces. Through experiments on multiple representative DLMs, we show that DLM-One achieves up to ∼\sim2000×\times speedup in sampling steps and ∼\sim500×\times in wall-clock time, while maintaining competitive performance on benchmark text generation tasks. We further analyze failure modes in language-domain diffusion distillation and propose an adversarially-regularized two-stage training scheme to prevent student degeneration. Our findings position one-step score distillation as a viable path for the efficient deployment of continuous diffusion models operating in continuous space for natural language processing.
May 28, 2025

Physics-Informed Distillation of Diffusion Models for PDE-Constrained Generation

Modeling physical systems in a generative manner offers several advantages, including the ability to handle partial observations, generate diverse solutions, and address both forward and inverse problems. Recently, diffusion models have gained increasing attention in the modeling of physical systems, particularly those governed by partial differential equations (PDEs). However, diffusion models only access noisy data xt\boldsymbol{x}_t at intermediate steps, making it infeasible to directly enforce constraints on the clean sample x0\boldsymbol{x}_0 at each noisy level. As a workaround, constraints are typically applied to the expectation of clean samples E[x0∣xt]\mathbb{E}[\boldsymbol{x}_0|\boldsymbol{x}_t], which is estimated using the learned score network. However, imposing PDE constraints on the expectation does not strictly represent the one on the true clean data, known as Jensen's Gap. This gap creates a trade-off: enforcing PDE constraints may come at the cost of reduced accuracy in generative modeling. To address this, we propose a simple yet effective post-hoc distillation approach, where PDE constraints are not injected directly into the diffusion process, but instead enforced during a post-hoc distillation stage. We term our method as Physics-Informed Distillation of Diffusion Models (PIDDM). This distillation not only facilitates single-step generation with improved PDE satisfaction, but also support both forward and inverse problem solving and reconstruction from randomly partial observation. Extensive experiments across various PDE benchmarks demonstrate that PIDDM significantly improves PDE satisfaction over several recent and competitive baselines, such as PIDM, DiffusionPDE, and ECI-sampling, with less computation overhead. Our approach can shed light on more efficient and effective strategies for incorporating physical constraints into diffusion models.
Feb 6, 2025

DICE: Distilling Classifier-Free Guidance into Text Embeddings

Text-to-image diffusion models are capable of generating high-quality images, but suboptimal pre-trained text representations often result in these images failing to align closely with the given text prompts. Classifier-free guidance (CFG) is a popular and effective technique for improving text-image alignment in the generative process. However, CFG introduces significant computational overhead. In this paper, we present DIstilling CFG by sharpening text Embeddings (DICE) that replaces CFG in the sampling process with half the computational complexity while maintaining similar generation quality. DICE distills a CFG-based text-to-image diffusion model into a CFG-free version by refining text embeddings to replicate CFG-based directions. In this way, we avoid the computational drawbacks of CFG, enabling high-quality, well-aligned image generation at a fast sampling speed. Furthermore, examining the enhancement pattern, we identify the underlying mechanism of DICE that sharpens specific components of text embeddings to preserve semantic information while enhancing fine-grained details. Extensive experiments on multiple Stable Diffusion v1.5 variants, SDXL, and PixArt-αα demonstrate the effectiveness of our method. Code is available at https://github.com/zju-pi/dice.