FlowCast: 为可扩展的零成本推测性流匹配进行轨迹预测
FlowCast: Trajectory Forecasting for Scalable Zero-Cost Speculative Flow Matching
AI总结：
FlowCast通过利用流匹配模型保持恒定速度的特性，实现无需训练的高效推理，提升图像生成等任务的速度2.5倍，同时保持质量。
摘要：
流匹配（FM）最近涌现出一种强大的方法，用于高质量的视觉生成。然而，由于大量的去噪步骤，其缓慢的推理限制了其在实时或交互应用中的潜在用途。现有的加速方法，如蒸馏、截断或一致性训练，要么降低质量，导致昂贵的重新训练，或缺乏泛化能力。我们提出了FlowCast，一种无需训练的推测生成框架，通过利用FM模型被训练以保持恒定速度的事实来加速推理。FlowCast通过推测当前速度的未来速度来加速推理，而无需产生额外的时间成本，并接受其在均方误差阈值内的结果。这种恒定速度预测允许在稳定区域中冗余步骤被积极跳过，同时在复杂区域中保持精度。FlowCast是一种即插即用的框架，可以无缝整合到任何FM模型中，并且不需要辅助网络。我们还提出了一个理论分析，并界定了推测和完整FM轨迹之间的最坏情况偏差。实证评估表明，FlowCast在图像生成、视频生成和编辑任务中实现了>2.5倍的速度提升，优于现有基线，在与标准完整生成相比时没有质量损失。
英文摘要：
Flow Matching (FM) has recently emerged as a powerful approach for high-quality visual generation. However, their prohibitively slow inference due to a large number of denoising steps limits their potential use in real-time or interactive applications. Existing acceleration methods, like distillation, truncation, or consistency training, either degrade quality, incur costly retraining, or lack generalization. We propose FlowCast, a training-free speculative generation framework that accelerates inference by exploiting the fact that FM models are trained to preserve constant velocity. FlowCast speculates future velocity by extrapolating current velocity without incurring additional time cost, and accepts it if it is within a mean-squared error threshold. This constant-velocity forecasting allows redundant steps in stable regions to be aggressively skipped while retaining precision in complex ones. FlowCast is a plug-and-play framework that integrates seamlessly with any FM model and requires no auxiliary networks. We also present a theoretical analysis and bound the worst-case deviation between speculative and full FM trajectories. Empirical evaluations demonstrate that FlowCast achieves $>2.5\times$ speedup in image generation, video generation, and editing tasks, outperforming existing baselines with no quality loss as compared to standard full generation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
