Motion Prompting: Controlling Video Generation with Motion Trajectories

TL;DR

This paper introduces motion prompts, a flexible method for controlling video generation using motion trajectories, enabling nuanced dynamic actions, scene control, and editing, with demonstrated applications and strong quantitative and human evaluation results.

Contribution

We propose motion prompts, a novel flexible motion conditioning method for video generation that encodes diverse trajectories and translates user requests into detailed motion controls.

Findings

Effective control of object and scene motion in generated videos.

Versatility demonstrated through applications like motion transfer and editing.

Strong quantitative and human evaluation results.

Abstract

Motion control is crucial for generating expressive and compelling video content; however, most existing video generation models rely mainly on text prompts for control, which struggle to capture the nuances of dynamic actions and temporal compositions. To this end, we train a video generation model conditioned on spatio-temporally sparse or dense motion trajectories. In contrast to prior motion conditioning work, this flexible representation can encode any number of trajectories, object-specific or global scene motion, and temporally sparse motion; due to its flexibility we refer to this conditioning as motion prompts. While users may directly specify sparse trajectories, we also show how to translate high-level user requests into detailed, semi-dense motion prompts, a process we term motion prompt expansion. We demonstrate the versatility of our approach through various applications, including camera and object motion control, "interacting" with an image, motion transfer, and image editing. Our results showcase emergent behaviors, such as realistic physics, suggesting the potential of motion prompts for probing video models and interacting with future generative world models. Finally, we evaluate quantitatively, conduct a human study, and demonstrate strong performance. Video results are available on our webpage: https://motion-prompting.github.io/