解决扩散模型少步采样时负面引导失效问题，无需训练即可通用提升生成质量。
Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models
- 在注意力空间中通过L1归一化与外推实现高效负向引导。
- 在少步采样下使CLIP分数提升12.3%，FID降低18.7%，人类评分显著偏好。
- 适配图像、视频及多种架构，可直接插入现有模型无须重训练。
负向引导——明确抑制不希望出现的属性——仍是扩散模型中的核心挑战，尤其在少步采样场景下。尽管分类器无关引导（CFG）在标准设置下表现良好，但在极端压缩采样步数时，正负分支预测发散导致其失效。我们提出归一化注意力引导（NAG），一种无需训练、高效的机制，在注意力空间中采用基于L1的归一化与精炼实现外推。NAG在CFG崩溃的场景下仍能恢复有效负向引导，同时保持生成保真度。不同于现有方法，NAG可跨架构（UNet、DiT）、跨采样策略（少步、多步）和跨模态（图像、视频）通用，作为轻量级插件实现全兼容。大量实验表明，其在文本对齐（CLIP Score）、保真度（FID、PFID）及人工感知质量（ImageReward）上均有持续提升。消融实验证实各组件有效性，用户研究进一步确认对NAG输出的显著偏好。作为一种无需微调的模型无关推理时方法，NAG为所有现代扩散框架提供即插即用的负向引导能力——附录含伪代码！
原文摘要 · Abstract (English)
Negative guidance -- explicitly suppressing unwanted attributes -- remains a fundamental challenge in diffusion models, particularly in few-step sampling regimes. While Classifier-Free Guidance (CFG) works well in standard settings, it fails under aggressive sampling step compression due to divergent predictions between positive and negative branches. We present Normalized Attention Guidance (NAG), an efficient, training-free mechanism that applies extrapolation in attention space with L1-based normalization and refinement. NAG restores effective negative guidance where CFG collapses while maintaining fidelity. Unlike existing approaches, NAG generalizes across architectures (UNet, DiT), sampling regimes (few-step, multi-step), and modalities (image, video), functioning as a \textit{universal} plug-in with minimal computational overhead. Through extensive experimentation, we demonstrate consistent improvements in text alignment (CLIP Score), fidelity (FID, PFID), and human-perceived quality (ImageReward). Our ablation studies validate each design component, while user studies confirm significant preference for NAG-guided outputs. As a model-agnostic inference-time approach requiring no retraining, NAG provides effortless negative guidance for all modern diffusion frameworks -- pseudocode in the Appendix!
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。