FlashMotion：基于轨迹引导的少步可控视频生成
FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance
将多步轨迹可控视频生成器蒸馏为少步版本，并设计扩散+对抗混合目标微调轨迹适配器，可直接复用于任何需要加速的可控视频生成管线；同时提出的 FlashBench 提供了长序列轨迹精度评测协议。
原文依据 we introduce FlashMotion, a novel training framework designed for few-step trajectory-controllable video generation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期，轨迹可控视频生成取得了显著进展。已有方法主要采用基于适配器的架构，沿预定义轨迹实现精确的运动控制。然而，这些方法都依赖多步去噪过程，导致大量时间冗余与计算开销。现有视频蒸馏方法虽能将多步生成器蒸馏为少步生成器，但直接将其应用于轨迹可控视频生成时，会在视频质量与轨迹精度两方面出现明显退化。为弥补这一差距，我们提出 FlashMotion，一种面向少步轨迹可控视频生成的新型训练框架。我们首先在多步视频生成器上训练轨迹适配器以实现精确的轨迹控制；随后将生成器蒸馏为少步版本以加速视频生成；最后采用结合扩散目标与对抗目标的混合策略微调适配器，使其与少步生成器对齐，从而生成高质量且轨迹准确的视频。在评测方面，我们提出 FlashBench，这是一个面向长序列轨迹可控视频生成的基准，可在不同前景物体数量下衡量视频质量与轨迹精度。在两个适配器架构上的实验表明，FlashMotion 在视觉质量与轨迹一致性上均优于现有视频蒸馏方法和此前的多步模型。
英文原文摘要 1527 字符
Recent advances in trajectory-controllable video generation have achieved remarkable progress. Previous methods mainly use adapter-based architectures for precise motion control along predefined trajectories.However, all these methods rely on a multi-step denoising process, leading to substantial time redundancy and computational overhead.While existing video distillation methods successfully distill multi-step generators into few-step, directly applying these approaches to trajectory-controllable video generation results in noticeable degradation in both video quality and trajectory accuracy.To bridge this gap, we introduce FlashMotion, a novel training framework designed for few-step trajectory-controllable video generation.We first train a trajectory adapter on a multi-step video generator for precise trajectory control.Then, we distill the generator into a few-step version to accelerate video generation.Finally, we finetune the adapter using a hybrid strategy that combines diffusion and adversarial objectives, aligning it with the few-step generator to produce high-quality, trajectory-accurate videos.For evaluation, we introduce FlashBench, a benchmark for long-sequence trajectory-controllable video generation that measures both video quality and trajectory accuracy across varying numbers of foreground objects. Experiments on two adapter architectures show that FlashMotion surpasses existing video distillation methods and previous multi-step models in both visual quality and trajectory consistency.