Mojito: Motion Trajectory and Intensity Control for Video Generation

TL;DR

Mojito is a novel diffusion model for text-to-video generation that enables precise control over motion trajectories and intensity, using efficient modules that leverage cross-attention and optical flow for realistic dynamic videos.

Contribution

Introduces Mojito, a diffusion-based framework with novel modules for directional motion control and intensity modulation, enhancing controllability and efficiency in text-to-video synthesis.

Findings

Achieves accurate motion trajectory control matching specified directions.

Effectively modulates motion intensity guided by optical flow.

Demonstrates high computational efficiency and realistic motion dynamics.

Abstract

Recent advancements in diffusion models have shown great promise in producing high-quality video content. However, efficiently training video diffusion models capable of integrating directional guidance and controllable motion intensity remains a challenging and under-explored area. To tackle these challenges, this paper introduces Mojito, a diffusion model that incorporates both motion trajectory and intensity control for text-to-video generation. Specifically, Mojito features a Directional Motion Control (DMC) module that leverages cross-attention to efficiently direct the generated object's motion without training, alongside a Motion Intensity Modulator (MIM) that uses optical flow maps generated from videos to guide varying levels of motion intensity. Extensive experiments demonstrate Mojito's effectiveness in achieving precise trajectory and intensity control with high computational efficiency, generating motion patterns that closely match specified directions and intensities, providing realistic dynamics that align well with natural motion in real-world scenarios.