qiqiApink/MotionGPT
The official PyTorch implementation of the paper "MotionGPT: Finetuned LLMs are General-Purpose Motion Generators"
This tool helps create realistic human motion animations from text descriptions. You input plain language text describing a movement, optionally with initial or key poses, and it outputs a corresponding animation of a 3D human figure in .npy and .gif formats. It's designed for animators, game developers, or researchers who need to generate human movements from textual prompts.
238 stars. No commits in the last 6 months.
Use this if you need to quickly generate specific human motion sequences based on textual descriptions, or if you want to experiment with controlling animations through natural language.
Not ideal if you require highly precise, manually keyframed animations or need to work with non-human characters.
Stars
238
Forks
18
Language
Python
License
—
Category
Last pushed
Dec 28, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/qiqiApink/MotionGPT"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AliHaiderAhmad001/GPT-from-Scratch-with-Tensorflow
Implementation for "Improving Language Understanding by Generative Pre-Training" paper
HomebrewML/HomebrewNLP-torch
A case study of efficient training of large language models using commodity hardware.
akshat0123/GPT-1
Pytorch implementation of GPT-1
nawnoes/pytorch-gpt-x
An implementation of an autoregressive language model using an improved Transformer and...
Shenggan/atp
Adaptive Tensor Parallelism for Foundation Models