showlab/MotionDirector
A text-to-video diffusion model research project that adapts pre-trained models to generate videos with desired motions from example video clips.
Not currently ranked — collecting fresh signals.
star history
MotionDirector customizes text-to-video diffusion models to produce videos with specific motions given reference video clips. The method uses lightweight fine-tuning to decouple appearance and motion, enabling customizable motion generation while preserving visual quality. Published at ECCV 2024 as an Oral presentation.
Frequently asked
- What is showlab/MotionDirector?
- A text-to-video diffusion model research project that adapts pre-trained models to generate videos with desired motions from example video clips.
- Is MotionDirector open source?
- Yes — showlab/MotionDirector is open source, released under the Apache-2.0 license.
- What language is MotionDirector written in?
- showlab/MotionDirector is primarily written in Python.
- How popular is MotionDirector?
- showlab/MotionDirector has 1k stars on GitHub.
- Where can I find MotionDirector?
- showlab/MotionDirector is on GitHub at https://github.com/showlab/MotionDirector.