DPM-Solver-v3：具有经验模型统计的改进扩散ODE求解器

DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics

October 20, 2023

作者: Kaiwen Zheng, Cheng Lu, Jianfei Chen, Jun Zhu

cs.AI

摘要

扩散概率模型（DPMs）在高保真图像生成方面表现出色，但存在采样效率低的问题。最近的研究通过提出利用DPMs特定ODE形式的快速ODE求解器来加速采样过程。然而，它们在推断过程中高度依赖特定参数化（如噪声/数据预测），这可能不是最佳选择。在这项工作中，我们提出了一种新的公式，朝向在采样过程中实现最佳参数化，以最小化ODE解的一阶离散化误差。基于这种公式，我们提出了DPM-Solver-v3，一种新的快速DPMs的ODE求解器，通过引入在预训练模型上高效计算的几个系数，我们称之为经验模型统计。我们进一步结合多步方法和预测校正框架，并提出一些技术，以改善在少量函数评估（NFE）或大指导尺度下的样本质量。实验证明，DPM-Solver-v3在无条件和有条件采样中，无论是像素空间还是潜在空间的DPMs中，特别是在5至10个NFE时，均实现了一贯更好或相当的性能。我们在无条件CIFAR10上实现了12.21（5 NFE）、2.51（10 NFE）的FID，以及在Stable Diffusion上实现了0.55（5 NFE，7.5指导尺度）的MSE，相较于先前的最先进无需训练的方法，加快了15%至30%的速度。代码可在https://github.com/thu-ml/DPM-Solver-v3找到。

English

Diffusion probabilistic models (DPMs) have exhibited excellent performance for high-fidelity image generation while suffering from inefficient sampling. Recent works accelerate the sampling procedure by proposing fast ODE solvers that leverage the specific ODE form of DPMs. However, they highly rely on specific parameterization during inference (such as noise/data prediction), which might not be the optimal choice. In this work, we propose a novel formulation towards the optimal parameterization during sampling that minimizes the first-order discretization error of the ODE solution. Based on such formulation, we propose DPM-Solver-v3, a new fast ODE solver for DPMs by introducing several coefficients efficiently computed on the pretrained model, which we call empirical model statistics. We further incorporate multistep methods and a predictor-corrector framework, and propose some techniques for improving sample quality at small numbers of function evaluations (NFE) or large guidance scales. Experiments show that DPM-Solver-v3 achieves consistently better or comparable performance in both unconditional and conditional sampling with both pixel-space and latent-space DPMs, especially in 5sim10 NFEs. We achieve FIDs of 12.21 (5 NFE), 2.51 (10 NFE) on unconditional CIFAR10, and MSE of 0.55 (5 NFE, 7.5 guidance scale) on Stable Diffusion, bringing a speed-up of 15\%sim30\% compared to previous state-of-the-art training-free methods. Code is available at https://github.com/thu-ml/DPM-Solver-v3.