Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sun, Yanxiao, Wu, Jiafu, Cao, Yun, Xu, Chengming, Wang, Yabiao, Cao, Weijian, Luo, Donghao, Wang, Chengjie, Fu, Yanwei
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.06082
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915497696559104
author Sun, Yanxiao
Wu, Jiafu
Cao, Yun
Xu, Chengming
Wang, Yabiao
Cao, Weijian
Luo, Donghao
Wang, Chengjie
Fu, Yanwei
author_facet Sun, Yanxiao
Wu, Jiafu
Cao, Yun
Xu, Chengming
Wang, Yabiao
Cao, Weijian
Luo, Donghao
Wang, Chengjie
Fu, Yanwei
contents Diffusion-based or flow-based models have achieved significant progress in video synthesis but require multiple iterative sampling steps, which incurs substantial computational overhead. While many distillation methods that are solely based on trajectory-preserving or distribution-matching have been developed to accelerate video generation models, these approaches often suffer from performance breakdown or increased artifacts under few-step settings. To address these limitations, we propose \textbf{\emph{SwiftVideo}}, a unified and stable distillation framework that combines the advantages of trajectory-preserving and distribution-matching strategies. Our approach introduces continuous-time consistency distillation to ensure precise preservation of ODE trajectories. Subsequently, we propose a dual-perspective alignment that includes distribution alignment between synthetic and real data along with trajectory alignment across different inference steps. Our method maintains high-quality video generation while substantially reducing the number of inference steps. Quantitative evaluations on the OpenVid-1M benchmark demonstrate that our method significantly outperforms existing approaches in few-step video generation.
format Preprint
id arxiv_https___arxiv_org_abs_2508_06082
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SwiftVideo: A Unified Framework for Few-Step Video Generation through Trajectory-Distribution Alignment
Sun, Yanxiao
Wu, Jiafu
Cao, Yun
Xu, Chengming
Wang, Yabiao
Cao, Weijian
Luo, Donghao
Wang, Chengjie
Fu, Yanwei
Computer Vision and Pattern Recognition
Diffusion-based or flow-based models have achieved significant progress in video synthesis but require multiple iterative sampling steps, which incurs substantial computational overhead. While many distillation methods that are solely based on trajectory-preserving or distribution-matching have been developed to accelerate video generation models, these approaches often suffer from performance breakdown or increased artifacts under few-step settings. To address these limitations, we propose \textbf{\emph{SwiftVideo}}, a unified and stable distillation framework that combines the advantages of trajectory-preserving and distribution-matching strategies. Our approach introduces continuous-time consistency distillation to ensure precise preservation of ODE trajectories. Subsequently, we propose a dual-perspective alignment that includes distribution alignment between synthetic and real data along with trajectory alignment across different inference steps. Our method maintains high-quality video generation while substantially reducing the number of inference steps. Quantitative evaluations on the OpenVid-1M benchmark demonstrate that our method significantly outperforms existing approaches in few-step video generation.
title SwiftVideo: A Unified Framework for Few-Step Video Generation through Trajectory-Distribution Alignment
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.06082