Through Diffusion Models (DMs), we have made significant advances in
generating high-quality images. Our exploration of these models delves deeply
into their core operational principles by systematically investigating key
aspects across various DM architectures: i) noise schedules, ii) samplers, and
iii) guidance. Our comprehensive examination of these models sheds light on
their hidden fundamental mechanisms, revealing the concealed foundational
elements that are essential for their effectiveness. Our analyses emphasize the
hidden key factors that determine model performance, offering insights that
contribute to the advancement of DMs. Past findings show that the configuration
of noise schedules, samplers, and guidance is vital to the quality of generated
images; however, models reach a stable level of quality across different
configurations at a remarkably similar point, revealing that the decisive
factors for optimal performance predominantly reside in the diffusion process
dynamics and the structural design of the model's network, rather than the
specifics of configuration details. Our comparative analysis reveals that
Denoising Diffusion Probabilistic Model (DDPM)-based diffusion dynamics
consistently outperform the Noise Conditioned Score Network (NCSN)-based ones,
not only when evaluated in their original forms but also when continuous
through Stochastic Differential Equation (SDE)-based implementations.

通过扩散模型（Diffusion Models），我们在生成高质量图像方面取得了重要进展，通过系统研究不同扩散模型架构的关键方面，如噪声调度、采样器和引导，我们深入探索了这些模型的核心操作原理。通过全面分析这些模型，我们揭示了它们隐藏的基础机制，揭示了对其有效性至关重要的隐藏关键因素。我们的分析强调了决定模型性能的隐藏关键因素，为扩散模型的发展提供了见解。

异形山谷：扩散模型的全面分析

The Uncanny Valley: A Comprehensive Analysis of Diffusion Models

Score-based generative models (or diffusion models for short) have proven
successful across many domains in generating text and image data. However, the
consideration of mixed-type tabular data with this model family has fallen
short so far. Existing research mainly combines different diffusion processes
without explicitly accounting for the feature heterogeneity inherent to tabular
data. In this paper, we combine score matching and score interpolation to
ensure a common type of continuous noise distribution that affects both
continuous and categorical features alike. Further, we investigate the impact
of distinct noise schedules per feature or per data type. We allow for
adaptive, learnable noise schedules to ensure optimally allocated model
capacity and balanced generative capability. Results show that our model
consistently outperforms state-of-the-art benchmark models and that accounting
for heterogeneity within the noise schedule design boosts the sample quality.

通过结合评分匹配和评分插值，我们在这篇论文中提出了一种针对混合类型表格数据的得分生成模型。模型考虑了特征异质性，并允许自适应、可学习的噪声调度以提高样本质量。实验结果表明，我们的模型在质量上始终优于最先进的基准模型，并且噪声调度设计中的异质性考虑提升了样本质量。

混合类型表格数据的连续扩散

Continuous Diffusion for Mixed-Type Tabular Data

Deep Generative Models (DGMs) are widely used to create innovative designs
across multiple industries, ranging from fashion to the automotive sector. In
addition to generating images of high visual quality, the task of structural
design generation imposes more stringent constrains on the semantic expression,
e.g., no floating material or missing part, which we refer to as plausibility
in this work. We delve into the impact of noise schedules of diffusion models
on the plausibility of the outcome: there exists a range of noise levels at
which the model's performance decides the result plausibility. Also, we propose
two techniques to determine such a range for a given image set and devise a
novel parametric noise schedule for better plausibility. We apply this noise
schedule to the training and sampling of the well-known diffusion model EDM and
compare it to its default noise schedule. Compared to EDM, our schedule
significantly improves the rate of plausible designs from 83.4% to 93.5% and
Fr\'echet Inception Distance (FID) from 7.84 to 4.87. Further applications of
advanced image editing tools demonstrate the model's solid understanding of
structure.

通过研究噪声计划对扩散模型的影响，我们提出了两种确定给定图像集合的合理噪声范围的技术，并设计了一种新的参数化噪声计划，以获得更好的合理性。将此噪声计划应用于已知的扩散模型 EDM 的训练和采样，并将其与默认噪声计划进行比较，结果显示我们的计划将可行设计从 83.4％提高到 93.5％，Fréchet Inception Distance（FID）从 7.84 降低到 4.87。进一步的高级图像编辑工具应用证明了该模型对结构的良好理解。