通过低频信号分析，解决扩散模型中高引导尺度带来的过度饱和问题。
Rethinking Oversaturation in Classifier-Free Guidance via Low Frequency
- 基于低频信号识别冗余信息位置，动态设定阈值。
- 在多款扩散模型上显著减少不真实伪影，提升生成质量。
- 适合追求高质量图像生成的开发者与研究者使用。
Classifier-free guidance（CFG）在条件扩散模型中通过引导尺度平衡条件与无条件项的影响，高引导尺度可增强条件项性能，但常导致过度饱和和不真实伪影。本文从低频信号角度重新审视该问题，发现冗余信息积累是主要原因。为此提出低频改进型无分类器引导（LF-CFG），通过自适应阈值测量定位冗余信息，依据前后步骤低频信息变化率确定合理阈值，并对低频信号中的冗余部分实施降权策略。实验表明，LF-CFG在Stable Diffusion-XL、Stable Diffusion 2.1、3.0、3.5及SiT-XL等多种扩散模型上均有效缓解了过度饱和与伪影问题。
原文摘要 · Abstract (English)
Classifier-free guidance (CFG) succeeds in condition diffusion models that use a guidance scale to balance the influence of conditional and unconditional terms. A high guidance scale is used to enhance the performance of the conditional term. However, the high guidance scale often results in oversaturation and unrealistic artifacts. In this paper, we introduce a new perspective based on low-frequency signals, identifying the accumulation of redundant information in these signals as the key factor behind oversaturation and unrealistic artifacts. Building on this insight, we propose low-frequency improved classifier-free guidance (LF-CFG) to mitigate these issues. Specifically, we introduce an adaptive threshold-based measurement to pinpoint the locations of redundant information. We determine a reasonable threshold by analyzing the change rate of low-frequency information between prior and current steps. We then apply a down-weight strategy to reduce the impact of redundant information in the low-frequency signals. Experimental results demonstrate that LF-CFG effectively alleviates oversaturation and unrealistic artifacts across various diffusion models, including Stable Diffusion-XL, Stable Diffusion 2.1, 3.0, 3.5, and SiT-XL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。