jpthu17/GraphMotion

[NeurIPS 2023] Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs

35
/ 100
Emerging

This project helps animators, game developers, or filmmakers generate highly specific character movements from text descriptions. You provide a phrase like "a person slowly walked forward," and the system outputs a detailed 3D animation of that action. It's designed for anyone needing precise control over animated human motion, from overall movement to subtle specifics.

128 stars. No commits in the last 6 months.

Use this if you need to create realistic and finely-tuned human animations based on textual input, with the ability to adjust individual aspects like speed or direction.

Not ideal if you are looking for a simple drag-and-drop animation tool or if you do not have a technical background in machine learning model training and configuration.

3D-animation character-design motion-capture game-development filmmaking
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

128

Forks

7

Language

Python

License

Apache-2.0

Last pushed

Nov 15, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/jpthu17/GraphMotion"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.