Recent advance in diffusion models incorporates the Stochastic Differential Equation (SDE), which brings the state-of-the art performance on image generation tasks. This paper improves such diffusion models by analyzing the model at the zero diffusion time. In real datasets, the score function diverges as the diffusion time ($t$) decreases to zero, and this observation leads an argument that the score estimation fails at $t=0$ with any neural network structure. Subsequently, we introduce Unbounded Diffusion Model (UDM) that resolves the score diverging problem with an easily applicable modification to any diffusion models. Additionally, we introduce a new SDE that overcomes the theoretic and practical limitations of Variance Exploding SDE. On top of that, the introduced Soft Truncation method improves the sample quality by mitigating the loss scale issue that happens at $t=0$. We further provide a theoretic result of the proposed method to uncover the behind mechanism of the diffusion models.

翻译：最新扩散模型的进步包括Stochatic different Equation (SDE), 它带来了图像生成任务的最新性能。 本文通过在零扩散时间分析模型来改进这种扩散模型。 在真实的数据集中, 分数函数随着扩散时间( t$) 降低到零而有所不同, 这一观察引出了这样一个论点: 任何神经网络结构的分数估计值以$t=0美元为单位计算失败。 随后, 我们引入了无限制Difmulation 模型( UDM), 解决分数差异问题, 对任何传播模型进行易于应用的修改。 此外, 我们引入了新的SDE, 克服了差异开发 SDE 的理论和实践局限性。 除此之外, 引入的 Soft 调整方法通过降低在$t=0美元上发生的损失规模问题, 提高了样本质量。 我们还提供了拟议方法的理论结果, 以发现扩散模型的后机制。