Diffusion models have found widespread adoption in various areas. However, their sampling process is slow because it requires hundreds to thousands of network evaluations to emulate a continuous process defined by differential equations. In this work, we use neural operators, an efficient method to solve the probability flow differential equations, to accelerate the sampling process of diffusion models. Compared to other fast sampling methods that have a sequential nature, we are the first to propose parallel decoding method that generates images with only one model forward pass. We propose \textit{diffusion model sampling with neural operator} (DSNO) that maps the initial condition, i.e., Gaussian distribution, to the continuous-time solution trajectory of the reverse diffusion process. To model the temporal correlations along the trajectory, we introduce temporal convolution layers that are parameterized in the Fourier space into the given diffusion model backbone. We show our method achieves state-of-the-art FID of 4.12 for CIFAR-10 and 8.35 for ImageNet-64 in the one-model-evaluation setting.

翻译：扩散模型已在多个领域得到广泛应用。然而，其采样过程较为缓慢，因为需要数百至数千次网络评估来模拟由微分方程定义的连续过程。在本工作中，我们采用神经算子这一高效求解概率流微分方程的方法来加速扩散模型的采样过程。与具有顺序特性的其他快速采样方法不同，我们首次提出仅需一次模型前向传播即可生成图像的并行解码方法。我们提出基于神经算子的扩散模型采样方法（DSNO），该方法将初始条件（即高斯分布）映射为逆扩散过程的连续时间解轨迹。为建模轨迹沿时间维度的相关性，我们在给定扩散模型骨干网络中引入傅里叶空间参数化的时序卷积层。实验表明，在单模型评估设定下，本方法在CIFAR-10数据集上实现了4.12的FID值，在ImageNet-64上实现了8.35的FID值，均达到领先水平。