Score-based generative models (SGMs) have recently emerged as a promising class of generative models. However, a fundamental limitation is that their sampling process is slow due to a need for many (\eg, $2000$) iterations of sequential computations. An intuitive acceleration method is to reduce the sampling iterations which however causes severe performance degradation. We assault this problem to the ill-conditioned issues of the Langevin dynamics and reverse diffusion in the sampling process. Under this insight, we propose a model-agnostic {\bf\em preconditioned diffusion sampling} (PDS) method that leverages matrix preconditioning to alleviate the aforementioned problem. PDS alters the sampling process of a vanilla SGM at marginal extra computation cost, and without model retraining. Theoretically, we prove that PDS preserves the output distribution of the SGM, no risk of inducing systematical bias to the original sampling process. We further theoretically reveal a relation between the parameter of PDS and the sampling iterations,easing the parameter estimation under varying sampling iterations. Extensive experiments on various image datasets with a variety of resolutions and diversity validate that our PDS consistently accelerates off-the-shelf SGMs whilst maintaining the synthesis quality. In particular, PDS can accelerate by up to $29\times$ on more challenging high resolution (1024$\times$1024) image generation. Compared with the latest generative models (\eg, CLD-SGM, DDIM, and Analytic-DDIM), PDS can achieve the best sampling quality on CIFAR-10 at a FID score of 1.99. Our code is made publicly available to foster any further research https://github.com/fudan-zvg/PDS.
翻译:最近,基于分数的基因变异模型(SGMS)作为一种有希望的基因变异模型(SGMS)出现了。然而,一个根本性的限制是,由于需要多次(geg, 2,000美元)顺序计算,其取样过程缓慢。一种直观的加速方法是减少抽样迭代,但又会导致严重性能退化。我们将这一问题归咎于Langevin动态和取样过程中反向扩散的不成熟问题。根据这一深入了解,我们建议采用一种模型-直观(bffcom)的扩展采样采样(DPDS)方法,利用矩阵来为缓解上述问题的先决条件。PDS改变香草SGM的采样过程,以少量额外计算成本进行,而不进行模型再培训。理论上,我们证明PDS保持SGM的输出分布,没有引起原采样过程系统偏差的风险。我们进一步从理论上揭示了PDSDS的参数与采样值之间的关系,在不同的取样中可以得出参数估计。在各种图像变现的PMS-RIMS-DS中进行了广泛的实验,在不断更新的SIMDSDS中可以加速进行。