In this paper, we propose Tortoise and Hare Guidance (THG), a training-free strategy that accelerates diffusion sampling while maintaining high-fidelity generation. We demonstrate that the noise estimate and the additional guidance term exhibit markedly different sensitivity to numerical error by reformulating the classifier-free guidance (CFG) ODE as a multirate system of ODEs. Our error-bound analysis shows that the additional guidance branch is more robust to approximation, revealing substantial redundancy that conventional solvers fail to exploit. Building on this insight, THG significantly reduces the computation of the additional guidance: the noise estimate is integrated with the tortoise equation on the original, fine-grained timestep grid, while the additional guidance is integrated with the hare equation only on a coarse grid. We also introduce (i) an error-bound-aware timestep sampler that adaptively selects step sizes and (ii) a guidance-scale scheduler that stabilizes large extrapolation spans. THG reduces the number of function evaluations (NFE) by up to 30% with virtually no loss in generation fidelity ($\Delta$ImageReward $\leq$ 0.032) and outperforms state-of-the-art CFG-based training-free accelerators under identical computation budgets. Our findings highlight the potential of multirate formulations for diffusion solvers, paving the way for real-time high-quality image synthesis without any model retraining. The source code is available at https://github.com/yhlee-add/THG.

翻译：本文提出一种无需训练的加速策略——龟兔引导（THG），在保持高保真生成的同时加速扩散采样过程。通过将无分类器引导（CFG）常微分方程重构为多速率常微分方程组，我们证明了噪声估计项与额外引导项对数值误差的敏感性存在显著差异。误差界分析表明，额外引导分支对近似更具鲁棒性，揭示了传统求解器未能利用的显著冗余性。基于这一发现，THG大幅减少了额外引导的计算量：噪声估计在原始细粒度时间步网格上通过龟式方程进行积分，而额外引导仅通过兔式方程在粗粒度网格上积分。我们还引入了（i）基于误差界感知的自适应时间步采样器，以及（ii）用于稳定大范围外推的引导尺度调度器。THG将函数评估次数（NFE）降低高达30%，且生成保真度几乎无损失（ΔImageReward ≤ 0.032），在相同计算预算下优于当前最先进的基于CFG的无训练加速方法。我们的研究凸显了多速率公式在扩散求解器中的潜力，为无需模型重训练的实时高质量图像合成开辟了新途径。源代码发布于 https://github.com/yhlee-add/THG。