---
title: "制导打破拟合算子：针对无分类器制导的终端拟合修复方法"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.07665v1"
permalink: "https://feed.astralor.com/items/itm_e27f11bfb0515872fb65d506"
published: "2026-07-08T17:21:51.000Z"
score: 73
channel: "ai"
tags: ["Classifier-Free Guidance","DDIM","Stable Diffusion","扩散模型"]
---

# 制导打破拟合算子：针对无分类器制导的终端拟合修复方法

## AI 点评

> 这篇论文值得关注，尤其对从事扩散模型采样器优化的研究者。它用简洁的数学揭示了CFG高引导失效的根源，并给出了一个零代价的修复。虽然修复不是万能药，但在追求高条件控制的应用中（如精准文本到图像生成）能直接提升稳定性和FID。

## 速览

无分类器制导（CFG）是扩散模型中增强条件控制的标准技术，但在高等引导强度下会出现过饱和与不稳定。本文通过渐近保持数值分析，证明DDIM步骤在无引导时是终端层的唯一拟合算子，而引导会使判别子空间恢复刚度为异常指数1+w，导致DDIM不再拟合。作者提出一种零额外NFE的修复：将CFG的方向项替换为r^(1+w)-r，消除发散项，在CIFAR-10和Stable Diffusion 1.5上实现高引导稳定，FID提升明显，但非通用质量提升。

## 关键点

- CFG在强引导下过饱和的根本原因是DDIM不再拟合被引导的算子，导致残差发散。
- 通过渐近分析导出引导时钟的三个有序步长阈值，并解释一步过饱和是求解器伪影。
- 提出单系数零额外NFE修复：将CFG方向项替换为r^(1+w)-r，消除sigma_min发散。
- 在CIFAR-10和Stable Diffusion 1.5上，修复后的方法在9/9网格点上FID优于标准CFG，但非通用质量提升。

## 全文

Classifier-free guidance (CFG) is the standard way to strengthen class-conditioning in diffusion and flow-matching samplers, yet at large guidance it oversaturates and destabilizes, symptoms practitioners suppress with more steps or limited-interval schedules. We analyze CFG through an asymptotic-preserving, numerical-analysis lens. Building on a recent result that the deterministic DDIM step is the unique fitted operator for the unguided terminal layer, exact on the final small-sigma stretch of sampling, we show that guidance re-stiffens exactly the discriminative subspace to an anomalous exponent 1+w. DDIM is therefore no longer fitted there, and on coarse meshes its guided residual diverges as sigma_min goes to zero. We prove a guided clock barrier with three ordered step-size thresholds, and read one-step oversaturation as its endpoint: a solver artifact on the calibration model rather than the continuous guided law. The same analysis yields a one-coefficient, zero-extra-NFE repair: replace CFG's w(r-1) by r^(1+w)-r on the guidance direction. On the calibration model's discriminative crossover, this removes CFG's sigma_min-divergent blow-up and is first-order accurate against the exact guided flow as sigma_min goes to zero. On learned CIFAR-10 checkpoints, and as a cross-domain smoke test on Stable Diffusion 1.5 DDIM, it acts as a high-guidance stabilizer at no extra cost rather than a universal quality knob: it cuts residual amplification and saturation, gives 9/9 point-FID wins over CFG on the tested grid, and preserves classifier-proxy target accuracy in the hard-cell blocks. We report the limits alongside: it is not a universal image-quality win, and against a dense vanilla-CFG reference it is not a uniformly better integrator of that field.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_e27f11bfb0515872fb65d506