mayuelala/FollowYourPose
A diffusion-based model that generates videos from text prompts guided by human pose sequences.
Not currently ranked — collecting fresh signals.
star history
Follow-Your-Pose is a pose-guided text-to-video generation system that creates videos based on textual descriptions while following the motion indicated by pose keypoints. The model learns to generate videos using pose-free reference videos during training, enabling pose-controllable video synthesis at inference time. It provides pretrained checkpoints, inference code, and a demo notebook for experimentation.
Frequently asked
- What is mayuelala/FollowYourPose?
- A diffusion-based model that generates videos from text prompts guided by human pose sequences.
- Is FollowYourPose open source?
- Yes — mayuelala/FollowYourPose is open source, released under the MIT license.
- What language is FollowYourPose written in?
- mayuelala/FollowYourPose is primarily written in Python.
- How popular is FollowYourPose?
- mayuelala/FollowYourPose has 1.4k stars on GitHub.
- Where can I find FollowYourPose?
- mayuelala/FollowYourPose is on GitHub at https://github.com/mayuelala/FollowYourPose.