arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.09970cs.LGstat.ML
收藏

加速扩散模型的并行采样

Accelerating Parallel Sampling of Diffusion Models

School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)理工学院);DAMO Academy, Alibaba Group(阿里巴巴集团达摩院);Shenzhen Research Institute of Big Data(深圳大数据研究院)

Zhiwei Tang, Jiasheng Tang, Hao Luo, Fan Wang, Tsung-Hui Chang

AI总结:

提出ParaTAA,一种无需训练的并行采样算法,通过将扩散模型采样转化为求解三角非线性方程组并利用不动点迭代,将推理步数减少4至14倍,显著加速采样。

摘要:

扩散模型已成为图像生成领域最先进的生成模型。然而,由于扩散模型采样过程固有的自回归特性,其采样通常非常耗时。在这项工作中,我们提出了一种新颖的方法,通过并行化自回归过程来加速扩散模型的采样。具体来说,我们将采样过程重新表述为通过不动点迭代求解三角非线性方程组。基于这一创新表述,我们探索了多种系统性技术,以进一步减少求解过程所需的迭代步数。应用这些技术,我们提出了ParaTAA,一种通用且无需训练的并行采样算法,能够利用额外的计算和内存资源来提高采样速度。我们的实验表明,ParaTAA可以将DDIM和DDPM等常见顺序采样算法所需的推理步数减少4至14倍。值得注意的是,当将ParaTAA应用于Stable Diffusion(一种广泛使用的文本到图像扩散模型)的100步DDIM时,仅需7步推理即可生成与顺序采样相同的图像。代码可在https://github.com/TZW1998/ParaTAA-Diffusion获取。

英文摘要:

Diffusion models have emerged as state-of-the-art generative models for image generation. However, sampling from diffusion models is usually time-consuming due to the inherent autoregressive nature of their sampling process. In this work, we propose a novel approach that accelerates the sampling of diffusion models by parallelizing the autoregressive process. Specifically, we reformulate the sampling process as solving a system of triangular nonlinear equations through fixed-point iteration. With this innovative formulation, we explore several systematic techniques to further reduce the iteration steps required by the solving process. Applying these techniques, we introduce ParaTAA, a universal and training-free parallel sampling algorithm that can leverage extra computational and memory resources to increase the sampling speed. Our experiments demonstrate that ParaTAA can decrease the inference steps required by common sequential sampling algorithms such as DDIM and DDPM by a factor of 4$\sim$14 times. Notably, when applying ParaTAA with 100 steps DDIM for Stable Diffusion, a widely-used text-to-image diffusion model, it can produce the same images as the sequential sampling in only 7 inference steps. The code is available at https://github.com/TZW1998/ParaTAA-Diffusion.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑