Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ke, Lei, Yin, Hubery, Liu, Gongye, Lv, Zhengyao, Guo, Jingcai, Li, Chen, Luo, Wenhan, Yang, Yujiu, Lyu, Jing
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.18834
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917100586532864
author Ke, Lei
Yin, Hubery
Liu, Gongye
Lv, Zhengyao
Guo, Jingcai
Li, Chen
Luo, Wenhan
Yang, Yujiu
Lyu, Jing
author_facet Ke, Lei
Yin, Hubery
Liu, Gongye
Lv, Zhengyao
Guo, Jingcai
Li, Chen
Luo, Wenhan
Yang, Yujiu
Lyu, Jing
contents With the success of flow matching in visual generation, sampling efficiency remains a critical bottleneck for its practical application. Among flow models' accelerating methods, ReFlow has been somehow overlooked although it has theoretical consistency with flow matching. This is primarily due to its suboptimal performance in practical scenarios compared to consistency distillation and score distillation. In this work, we investigate this issue within the ReFlow framework and propose FlowSteer, a method unlocks the potential of ReFlow-based distillation by guiding the student along teacher's authentic generation trajectories. We first identify that Piecewised ReFlow's performance is hampered by a critical distribution mismatch during the training and propose Online Trajectory Alignment(OTA) to resolve it. Then, we introduce a adversarial distillation objective applied directly on the ODE trajectory, improving the student's adherence to the teacher's generation trajectory. Furthermore, we find and fix a previously undiscovered flaw in the widely-used FlowMatchEulerDiscreteScheduler that largely degrades few-step inference quality. Our experiment result on SD3 demonstrates our method's efficacy.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18834
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FlowSteer: Guiding Few-Step Image Synthesis with Authentic Trajectories
Ke, Lei
Yin, Hubery
Liu, Gongye
Lv, Zhengyao
Guo, Jingcai
Li, Chen
Luo, Wenhan
Yang, Yujiu
Lyu, Jing
Computer Vision and Pattern Recognition
Artificial Intelligence
With the success of flow matching in visual generation, sampling efficiency remains a critical bottleneck for its practical application. Among flow models' accelerating methods, ReFlow has been somehow overlooked although it has theoretical consistency with flow matching. This is primarily due to its suboptimal performance in practical scenarios compared to consistency distillation and score distillation. In this work, we investigate this issue within the ReFlow framework and propose FlowSteer, a method unlocks the potential of ReFlow-based distillation by guiding the student along teacher's authentic generation trajectories. We first identify that Piecewised ReFlow's performance is hampered by a critical distribution mismatch during the training and propose Online Trajectory Alignment(OTA) to resolve it. Then, we introduce a adversarial distillation objective applied directly on the ODE trajectory, improving the student's adherence to the teacher's generation trajectory. Furthermore, we find and fix a previously undiscovered flaw in the widely-used FlowMatchEulerDiscreteScheduler that largely degrades few-step inference quality. Our experiment result on SD3 demonstrates our method's efficacy.
title FlowSteer: Guiding Few-Step Image Synthesis with Authentic Trajectories
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2511.18834