Saved in:
Bibliographic Details
Main Authors: Bajpai, Divya Jyoti, Agarwal, Shubham, Saxena, Apoorv, Kulkarni, Kuldeep, Mitra, Subrata, Hanawal, Manjesh Kumar
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.01329
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915767394500608
author Bajpai, Divya Jyoti
Agarwal, Shubham
Saxena, Apoorv
Kulkarni, Kuldeep
Mitra, Subrata
Hanawal, Manjesh Kumar
author_facet Bajpai, Divya Jyoti
Agarwal, Shubham
Saxena, Apoorv
Kulkarni, Kuldeep
Mitra, Subrata
Hanawal, Manjesh Kumar
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_01329
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FlowCast: Trajectory Forecasting for Scalable Zero-Cost Speculative Flow Matching
Bajpai, Divya Jyoti
Agarwal, Shubham
Saxena, Apoorv
Kulkarni, Kuldeep
Mitra, Subrata
Hanawal, Manjesh Kumar
Computer Vision and Pattern Recognition
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.
title FlowCast: Trajectory Forecasting for Scalable Zero-Cost Speculative Flow Matching
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.01329