FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance

TL;DR

FlashMotion introduces a training framework that enables few-step, trajectory-controllable video generation with high quality and accuracy, significantly reducing computational overhead compared to multi-step methods.

Contribution

The paper proposes a novel training framework combining trajectory adapter training, generator distillation, and hybrid finetuning to improve efficiency and quality in trajectory-controllable video generation.

Findings

Outperforms existing methods in visual quality and trajectory accuracy.

Reduces generation steps, improving efficiency.

Introduces FlashBench benchmark for evaluation.

Abstract

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.