让视频生成只需几步就能保持高质量，靠的是轨迹与分布双重对齐。
SwiftVideo: A Unified Framework for Few-Step Video Generation through Trajectory-Distribution Alignment
- 通过连续时间一致性蒸馏，精准保留微分方程轨迹。
- 在少步生成下，比现有方法显著提升视频质量，尤其在OpenVid-1M上表现优异。
- 适合需要快速生成高质量视频的场景，如实时应用或资源受限环境。
基于扩散或流模型的视频生成已取得显著进展，但需多步迭代采样，计算开销大。许多仅依赖轨迹保持或分布匹配的蒸馏方法虽加速生成，但在少步设置下易性能崩溃或引入伪影。为此，我们提出 extbf{ extit{SwiftVideo}}，一个统一且稳定的蒸馏框架，融合轨迹保持与分布匹配优势。通过引入连续时间一致性蒸馏，确保微分方程轨迹精确保留；进一步提出双视角对齐：合成数据与真实数据间的分布对齐，以及不同推理步长间的轨迹对齐。该方法在大幅减少推理步数的同时，仍保持高质量视频生成。在OpenVid-1M基准上的定量评估表明，本方法在少步视频生成中显著优于现有方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。