{"ID":2884602,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.06082","arxiv_id":"2508.06082","title":"SwiftVideo: A Unified Framework for Few-Step Video Generation through Trajectory-Distribution Alignment","abstract":"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.","short_abstract":"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 accele...","url_abs":"https://arxiv.org/abs/2508.06082","url_pdf":"https://arxiv.org/pdf/2508.06082v2","authors":"[\"Yanxiao Sun\",\"Jiafu Wu\",\"Yun Cao\",\"Chengming Xu\",\"Yabiao Wang\",\"Weijian Cao\",\"Donghao Luo\",\"Chengjie Wang\",\"Yanwei Fu\"]","published":"2025-08-08T07:26:34Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}