Diffusion models have emerged as powerful generative tools, rivaling GANs in sample quality and mirroring the likelihood scores of autoregressive models. A subset of these models, exemplified by DDIMs, exhibit an inherent asymmetry: they are trained over $T$ steps but only sample from a subset of $T$ during generation. This selective sampling approach, though optimized for speed, inadvertently misses out on vital information from the unsampled steps, leading to potential compromises in sample quality. To address this issue, we present the S$^{2}$-DMs, which is a new training method by using an innovative $L_{skip}$, meticulously designed to reintegrate the information omitted during the selective sampling phase. The benefits of this approach are manifold: it notably enhances sample quality, is exceptionally simple to implement, requires minimal code modifications, and is flexible enough to be compatible with various sampling algorithms. On the CIFAR10 dataset, models trained using our algorithm showed an improvement of 3.27% to 14.06% over models trained with traditional methods across various sampling algorithms (DDIMs, PNDMs, DEIS) and different numbers of sampling steps (10, 20, ..., 1000). On the CELEBA dataset, the improvement ranged from 8.97% to 27.08%. Access to the code and additional resources is provided in the github.

翻译：扩散模型已成为强大的生成工具，在样本质量上可与GANs媲美，在似然分数上则与自回归模型相当。此类模型中的子集（以DDIMs为代表）表现出固有不对称性：它们经过$T$步训练，但在生成过程中仅从$T$的子集中进行采样。这种选择性采样策略虽为速度优化，却无意中遗漏了未采样步骤中的关键信息，导致样本质量可能受损。为解决该问题，我们提出S$^{2}$-DMs，这是一种采用创新性$L_{skip}$的新训练方法，该方法精心设计以重新整合选择性采样阶段被忽略的信息。该方法的优势是多方面的：它显著提升了样本质量，实现起来极其简单，所需代码改动极少，且灵活性足以兼容多种采样算法。在CIFAR10数据集上，使用我们算法训练的模型在不同采样算法（DDIMs、PNDMs、DEIS）和不同采样步数（10、20、...、1000）下，相较于传统方法训练的模型性能提升达3.27%至14.06%。在CELEBA数据集上，性能提升范围为8.97%至27.08%。代码及更多资源可在GitHub上获取。