FlowCast: Trajectory Forecasting for Scalable Zero-Cost Speculative Flow Matching
This addresses the scalability issue for real-time or interactive applications using Flow Matching models, offering a plug-and-play solution without retraining, though it is incremental as it builds on existing FM methods.
The paper tackles the slow inference problem of Flow Matching models by proposing FlowCast, a training-free speculative generation framework that accelerates inference by exploiting constant-velocity properties, achieving over 2.5x speedup in image generation, video generation, and editing tasks with no quality loss.
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.