去噪即路径规划：基于 DPCache 的扩散模型免训练加速
Denoising as Path Planning: Training-Free Acceleration of Diffusion Models with DPCache
把扩散采样中「跳过哪些时间步」从局部启发式升级为基于路径代价张量 + 动态规划的全局调度，可直接套用到 DiT/FLUX/视频扩散等任意迭代采样器的免训练加速上，是缓存类加速方法（DeepCache、TeaCache 等）的通用改进思路。
原文依据 DPCache employs dynamic programming to select an optimal sequence of key timesteps that minimizes the total path cost while preserving trajectory fidelity.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论扩散模型在图像与视频生成上取得了显著成功，但其多步迭代采样带来的巨大计算开销仍制约着实际部署。在各类加速策略中，基于缓存的方法通过跨时间步复用或预测特征，提供了一种免训练且有效的解决方案。然而，现有方法依赖固定或局部自适应的调度方案，未考虑去噪轨迹的全局结构，往往导致误差累积与视觉伪影。为克服这一局限，我们提出 DPCache，一种全新的免训练加速框架，将扩散采样加速建模为全局路径规划问题。DPCache 利用一个小规模校准集构建路径感知代价张量，用以量化在前序关键时间步条件下跳过某些时间步所带来的路径相关误差。借助该张量，DPCache 采用动态规划选取最优的关键时间步序列，在保持轨迹保真度的同时最小化总路径代价。推理时，模型仅在这些关键时间步执行完整计算，中间输出则通过缓存特征高效预测。在 DiT、FLUX 与 HunyuanVideo 上的大量实验表明，DPCache 在极小质量损失下实现了显著加速，在 FLUX 上以 4.87 倍加速取得比先前加速方法高 +0.031 的 ImageReward，甚至在 3.54 倍加速下比全步基线高出 +0.028 的 ImageReward，验证了该路径感知全局调度框架的有效性。代码已开源：https://github.com/argsss/DPCache。
英文原文摘要 1688 字符
Diffusion models have demonstrated remarkable success in image and video generation, yet their practical deployment remains hindered by the substantial computational overhead of multi-step iterative sampling. Among acceleration strategies, caching-based methods offer a training-free and effective solution by reusing or predicting features across timesteps. However, existing approaches rely on fixed or locally adaptive schedules without considering the global structure of the denoising trajectory, often leading to error accumulation and visual artifacts. To overcome this limitation, we propose DPCache, a novel training-free acceleration framework that formulates diffusion sampling acceleration as a global path planning problem. DPCache constructs a Path-Aware Cost Tensor from a small calibration set to quantify the path-dependent error of skipping timesteps conditioned on the preceding key timestep. Leveraging this tensor, DPCache employs dynamic programming to select an optimal sequence of key timesteps that minimizes the total path cost while preserving trajectory fidelity. During inference, the model performs full computations only at these key timesteps, while intermediate outputs are efficiently predicted using cached features. Extensive experiments on DiT, FLUX, and HunyuanVideo demonstrate that DPCache achieves strong acceleration with minimal quality loss, outperforming prior acceleration methods by +0.031 ImageReward at 4.87x speedup and even surpassing the full-step baseline by +0.028 ImageReward at 3.54x speedup on FLUX, validating the effectiveness of our path-aware global scheduling framework. Code is available at https://github.com/argsss/DPCache.