CFG-Ctrl：基于控制的免分类器扩散引导
CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance
把 CFG 重新解释为对一阶连续时间生成流的控制，并用滑模控制替代线性 P 控制，可直接替换 Stable Diffusion 3.5、Flux、Qwen-Image 等流式扩散模型中的采样引导环节，在大引导尺度下抑制过冲、提升语义对齐。
原文依据 we introduce Sliding Mode Control CFG (SMC-CFG), which enforces the generative flow toward a rapidly convergent sliding manifold
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论免分类器引导（CFG）已成为增强基于流的扩散模型中语义对齐的核心方法。本文将 CFG 重新解释为施加于一阶连续时间生成流之上的控制，利用条件与无条件之间的差异作为误差信号来调整速度场，并由此提出统一框架 CFG-Ctrl。在这一视角下，我们将原始 CFG 归纳为固定增益的比例控制器（P 控制），而典型的后续变体则是在此基础上发展出的扩展控制律设计。然而，现有方法主要依赖线性控制，这本质上会导致不稳定、过冲以及语义保真度下降，在大引导尺度下尤为明显。为解决该问题，我们提出滑模控制 CFG（SMC-CFG），它驱使生成流趋向一个快速收敛的滑模面。具体而言，我们在语义预测误差上定义指数滑模面，并引入切换控制项以建立非线性反馈引导的校正。此外，我们给出李雅普诺夫稳定性分析，从理论上支撑有限时间收敛。在包括 Stable Diffusion 3.5、Flux 和 Qwen-Image 在内的文本到图像生成模型上的实验表明，SMC-CFG 在语义对齐上优于标准 CFG，并在较宽的引导尺度范围内增强了鲁棒性。
英文原文摘要 1431 字符
Classifier-Free Guidance (CFG) has emerged as a central approach for enhancing semantic alignment in flow-based diffusion models. In this paper, we explore a unified framework called **CFG-Ctrl**, which reinterprets CFG as a control applied to the first-order continuous-time generative flow, using the conditional-unconditional discrepancy as an error signal to adjust the velocity field. From this perspective, we summarize vanilla CFG as a proportional controller (P-control) with fixed gain, and typical follow-up variants develop extended control-law designs derived from it. However, existing methods mainly rely on linear control, inherently leading to instability, overshooting, and degraded semantic fidelity especially on large guidance scales. To address this, we introduce Sliding Mode Control CFG (**SMC-CFG**), which enforces the generative flow toward a rapidly convergent sliding manifold. Specifically, we define an exponential sliding mode surface over the semantic prediction error and introduce a switching control term to establish nonlinear feedback-guided correction. Moreover, we provide a Lyapunov stability analysis to theoretically support finite-time convergence. Experiments across text-to-image generation models including Stable Diffusion 3.5, Flux, and Qwen-Image demonstrate that SMC-CFG outperforms standard CFG in semantic alignment and enhances robustness across a wide range of guidance scales.