Classifier-Free Guidance (CFG) improves sample quality in diffusion models, but its dual-pass inference and reliance on null-condition training limit its use in few-step regimes. Attention-space guidance has emerged as a complementary paradigm that addresses this gap, yet why prior sparse-vs-dense attention guidance works remains elusive. We address this by analyzing attention extrapolation through Modern Hopfield dynamics, proving two directional properties of the sparse-dense discrepancy under shared conditioning that together certify it as a directionally consistent acceleration signal. Building on this, we propose Geometry-Aware Attention Guidance (GAG), a training-free, plug-and-play extrapolation rule that decomposes the discrepancy into parallel and orthogonal components relative to the retrieval direction, amplifying the convergence-aligned component while suppressing off-manifold noise; stability follows from a weak contraction property. We further provide an interpretation of this extrapolation as first-order Anderson Acceleration in attention space, offering a unified perspective on attention extrapolation methods. GAG is a universal method that generalizes across architectures (UNet, MMDiT) and sampling regimes (multi-step, few-step), consistently improving generation quality on diverse backbones, including FLUX.1, the recent FLUX.2, and Qwen-Image, with minimal computational overhead.

翻译：无分类器引导（CFG）通过双通道推理和空条件训练提升扩散模型的样本质量，但这两项特性限制了其在少步生成场景中的应用。注意力空间引导作为一种互补范式已涌现以弥补该不足，然而先前基于稀疏/稠密注意力引导的工作原理仍不明确。本文通过现代Hopfield动力学分析注意力外推机制，证明了共享条件下稀疏-稠密差异的两个方向性性质，进而验证其可作为方向一致的加速信号。基于此，我们提出几何感知注意力引导（GAG）——一种免训练、即插即用的外推规则：将差异分解为沿检索方向的平行分量与正交分量，增强对齐收敛方向的分量同时抑制流形外噪声，其稳定性由弱收缩性质保证。我们进一步将该外推机制解释为注意力空间中的一阶安德森加速，为注意力外推方法提供了统一视角。GAG是一种通用方法，可跨架构（UNet、MMDiT）与采样范式（多步、少步）泛化，在包括FLUX.1、最新FLUX.2及Qwen-Image在内的多样化骨干网络上持续提升生成质量，且仅引入极小计算开销。