Mael-zys/T2M-GPT
T2M-GPT is a text-conditional generative model that produces 3D human skeletal motion animations from natural language descriptions.
Not currently ranked — collecting fresh signals.
star history
This repository implements T2M-GPT, a CVPR 2023 paper that generates human motion sequences from text prompts. It uses a VQ-VAE to learn discrete motion tokens from motion capture data, then employs a GPT-style transformer to autoregressively generate motion tokens from text-derived features. The model maps textual descriptions like ‘a man steps forward and does a handstand’ into corresponding skeletal animation sequences that can be rendered as SMPL meshes.
Frequently asked
- What is Mael-zys/T2M-GPT?
- T2M-GPT is a text-conditional generative model that produces 3D human skeletal motion animations from natural language descriptions.
- Is T2M-GPT open source?
- Yes — Mael-zys/T2M-GPT is open source, released under the Apache-2.0 license.
- What language is T2M-GPT written in?
- Mael-zys/T2M-GPT is primarily written in Python.
- How popular is T2M-GPT?
- Mael-zys/T2M-GPT has 771 stars on GitHub.
- Where can I find T2M-GPT?
- Mael-zys/T2M-GPT is on GitHub at https://github.com/Mael-zys/T2M-GPT.