Skip to content

Boximator

Control video motion with text prompts and box constraints

Visit official site

What Boximator is

The tool is described as a smart video synthesis tool developed by Jiawei Wang, Yuchen Zhang and others, using deep learning to generate rich and controllable video motion from text prompts and extra box constraints, while letting users create distinctive video scenes from examples or custom text with box constraints described as giving more flexible motion control than other methods.

What you can do with it

  • Generate rich and controllable video motion
  • Add text prompts plus extra box constraints
  • Create video scenes from examples or custom text
  • Use deep learning techniques for video synthesis

Example uses

  • Pair an image with a description of a cute 3D boy standing then walking
  • Pair an image with a description of wind blowing away a woman's umbrella on a rainy day
  • Pair an image with a description of a man taking a rose from his pocket with his right hand

Pros & cons

✓ What we like

  • Box constraints from text prompts are described as more flexible than other methods
  • Deep learning is used to generate the motion

! What to watch out for

  • Each listed workflow starts from an image and a text description
  • Box constraints are added on top of the text prompts

FAQ

How is motion controlled?

The material describes adding text prompts and extra box constraints to generate controllable video motion.

What do the examples start from?

Each listed example pairs one image with a written description that becomes a video.

Last reviewed: 2026-11-15

More AI video generation tools

View all →

How we review