Optimal Stepsize for Diffusion Sampling
Diffusion models achieve remarkable generation quality but suffer from computational intensive sampling due to suboptimal step discretization. While existing works focus on optimizing denoising directions, we address the principled design of stepsize schedules. This paper proposes Optimal Stepsize Distillation, a dynamic programming framework that extracts theoretically optimal schedules by distilling knowledge from reference trajectories. By reformulating stepsize optimization as recursive error minimization, our method guarantees global discretization bounds through optimal substructure exploitation. Crucially, the distilled schedules demonstrate strong robustness across architectures, ODE solvers, and noise schedules. Experiments show 10x accelerated text-to-image generation while preserving 99.4% performance on GenEval. Our code is available at https://github.com/bebebe666/OptimalSteps.
Code (1)
Tasks
DenoisingImage GenerationText to Image GenerationText-to-Image GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SGD: General Analysis and Improved Rates
We propose a general yet simple theorem describing the convergence of SGD under the arbitrary sampling paradigm. Our theorem describes the convergence of an infinite array of variants of SGD, each of which is associated …
Non-Asymptotic Guarantees for Average-Reward Q-Learning with Adaptive Stepsizes
This work presents the first finite-time analysis for the last-iterate convergence of average-reward Q-learning with an asynchronous implementation. A key feature of the algorithm we study is the use of adaptive stepsize…
Q-LearningBellman Optimal Stepsize Straightening of Flow-Matching Models
Flow matching is a powerful framework for generating high-quality samples in various applications, especially image synthesis. However, the intensive computational demands of these models, especially during the finetunin…
Image GenerationBELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models
The inversion of diffusion model sampling, which aims to find the corresponding initial noise of a sample, plays a critical role in various tasks. Recently, several heuristic exact inversion samplers have been proposed t…
From Score Matching to Diffusion: A Fine-Grained Error Analysis in the Gaussian Setting
Sampling from an unknown distribution, accessible only through discrete samples, is a fundamental problem at the core of generative AI. The current state-of-the-art methods follow a two-step process: first, estimating th…
Denoising