自适应修正缓存，让扩散模型生成更准更快
AdaCorrection: Adaptive Offset Cache Correction for Accurate Diffusion Transformers
- 动态估计缓存有效性，按需混合旧与新激活值
- 保持接近原始的图像质量（近原FID），实现适度加速
- 无需额外训练，可直接集成到现有加速框架中
扩散Transformer（DiTs）在高保真图像和视频生成任务中表现优异，但其迭代去噪结构导致推理成本高昂。现有加速方法通过缓存中间特征提升效率，但依赖静态重用策略或粗粒度启发式规则，常引发时间漂移与缓存错位，显著降低生成质量。本文提出AdaCorrection，一种自适应偏移缓存修正框架，在扩散推理过程中跨层高效复用缓存的同时保持高质量生成。每一步骤中，AdaCorrection利用轻量级时空信号估计缓存有效性，并自适应融合缓存与新激活值。该修正过程实时计算，无需额外监督或再训练。实验表明，该方法在图像与视频扩散基准上均显著提升生成性能，保持近原生FID的同时实现适度加速。代码已集成至FastCache-xDiT（https://github.com/NoakLiu/FastCache-xDiT）。
原文摘要 · Abstract (English)
Diffusion Transformers (DiTs) achieve state-of-the-art performance in high-fidelity image and video generation but suffer from expensive inference due to their iterative denoising structure. While prior methods accelerate sampling by caching intermediate features, they rely on static reuse schedules or coarse-grained heuristics, which often lead to temporal drift and cache misalignment that significantly degrade generation quality. We introduce \textbf{AdaCorrection}, an adaptive offset cache correction framework that maintains high generation fidelity while enabling efficient cache reuse across Transformer layers during diffusion inference. At each timestep, AdaCorrection estimates cache validity with lightweight spatio-temporal signals and adaptively blends cached and fresh activations. This correction is computed on-the-fly without additional supervision or retraining. Our approach achieves strong generation quality with minimal computational overhead, maintaining near-original FID while providing moderate acceleration. Experiments on image and video diffusion benchmarks show that AdaCorrection consistently improves generation performance. Our code has been integrated into FastCache-xDiT at https://github.com/NoakLiu/FastCache-xDiT.
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。