Notice: This codebase is the SMPL-X verison of the original T2M-GPT work

For more information, please refer to our work FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructions.

We have devoted significant effort to training this version of the model very carefully. So if you find this version useful, please cite our work along with the original T2M-GPT paper:

@article{DBLP:journals/corr/abs-2601-12799,
  author       = {Peng Li and
                  Zihan Zhuang and
                  Yangfan Gao and
                  Yi Dong and
                  Sixian Li and
                  Changhao Jiang and
                  Shihan Dou and
                  Zhiheng Xi and
                  Enyu Zhou and
                  Jixuan Huang and
                  Hui Li and
                  Jingjing Gong and
                  Xingjun Ma and
                  Tao Gui and
                  Zuxuan Wu and
                  Qi Zhang and
                  Xuanjing Huang and
                  Yu{-}Gang Jiang and
                  Xipeng Qiu},
  title        = {FRoM-W1: Towards General Humanoid Whole-Body Control with Language
                  Instructions},
  journal      = {CoRR},
  volume       = {abs/2601.12799},
  year         = {2026},
  url          = {https://doi.org/10.48550/arXiv.2601.12799},
  doi          = {10.48550/ARXIV.2601.12799},
  eprinttype   = {arXiv},
  eprint       = {2601.12799},
  timestamp    = {Tue, 24 Mar 2026 08:45:06 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2601-12799.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

(CVPR 2023) T2M-GPT

Pytorch implementation of paper "T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations"

[Project Page] [Paper] [Notebook Demo] [HuggingFace] [Space Demo] [T2M-GPT+]

If our project is helpful for your research, please consider citing :

@inproceedings{zhang2023generating,
  title={T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations},
  author={Zhang, Jianrong and Zhang, Yangsong and Cun, Xiaodong and Huang, Shaoli and Zhang, Yong and Zhao, Hongwei and Lu, Hongtao and Shen, Xi},
  booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2023},
}

Table of Content

• 1. Visual Results
• 2. Installation
• 3. Quick Start
• 4. Train
• 5. Evaluation
• 6. SMPL Mesh Rendering
• 7. Acknowledgement
• 8. ChangLog

1. Visual Results (More results can be found in our project page)

Text: a man steps forward and does a handstand.
GT	T2M	MDM	MotionDiffuse	Ours
Text: A man rises from the ground, walks in a circle and sits back down on the ground.
GT	T2M	MDM	MotionDiffuse	Ours

2. Installation

2.1. Environment

Our model can be learnt in a single GPU V100-32G

conda env create -f environment.yml
conda activate T2M-GPT

The code was tested on Python 3.8 and PyTorch 1.8.1.

2.2. Dependencies

bash dataset/prepare/download_glove.sh

2.3. Datasets

We are using two 3D human motion-language dataset: HumanML3D and KIT-ML. For both datasets, you could find the details as well as download link [here].

Take HumanML3D for an example, the file directory should look like this:

./dataset/HumanML3D/
├── new_joint_vecs/
├── texts/
├── Mean.npy # same as in [HumanML3D](https://github.com/EricGuo5513/HumanML3D) 
├── Std.npy # same as in [HumanML3D](https://github.com/EricGuo5513/HumanML3D) 
├── train.txt
├── val.txt
├── test.txt
├── train_val.txt
└── all.txt

2.4. Motion & text feature extractors:

We use the same extractors provided by t2m to evaluate our generated motions. Please download the extractors.

bash dataset/prepare/download_extractor.sh

2.5. Pre-trained models

The pretrained model files will be stored in the 'pretrained' folder:

bash dataset/prepare/download_model.sh

2.6. Render SMPL mesh (optional)

If you want to render the generated motion, you need to install:

sudo sh dataset/prepare/download_smpl.sh
conda install -c menpo osmesa
conda install h5py
conda install -c conda-forge shapely pyrender trimesh mapbox_earcut

3. Quick Start

A quick start guide of how to use our code is available in demo.ipynb

4. Train

Note that, for kit dataset, just need to set '--dataname kit'.

4.1. VQ-VAE

The results are saved in the folder output.

python3 train_vq.py \
--batch-size 256 \
--lr 2e-4 \
--total-iter 300000 \
--lr-scheduler 200000 \
--nb-code 512 \
--down-t 2 \
--depth 3 \
--dilation-growth-rate 3 \
--out-dir output \
--dataname t2m \
--vq-act relu \
--quantizer ema_reset \
--loss-vel 0.5 \
--recons-loss l1_smooth \
--exp-name VQVAE

4.2. GPT

The results are saved in the folder output.

python3 train_t2m_trans.py  \
--exp-name GPT \
--batch-size 128 \
--num-layers 9 \
--embed-dim-gpt 1024 \
--nb-code 512 \
--n-head-gpt 16 \
--block-size 51 \
--ff-rate 4 \
--drop-out-rate 0.1 \
--resume-pth output/VQVAE/net_last.pth \
--vq-name VQVAE \
--out-dir output \
--total-iter 300000 \
--lr-scheduler 150000 \
--lr 0.0001 \
--dataname t2m \
--down-t 2 \
--depth 3 \
--quantizer ema_reset \
--eval-iter 10000 \
--pkeep 0.5 \
--dilation-growth-rate 3 \
--vq-act relu

5. Evaluation

5.1. VQ-VAE

python3 VQ_eval.py \
--batch-size 256 \
--lr 2e-4 \
--total-iter 300000 \
--lr-scheduler 200000 \
--nb-code 512 \
--down-t 2 \
--depth 3 \
--dilation-growth-rate 3 \
--out-dir output \
--dataname t2m \
--vq-act relu \
--quantizer ema_reset \
--loss-vel 0.5 \
--recons-loss l1_smooth \
--exp-name TEST_VQVAE \
--resume-pth output/VQVAE/net_last.pth

5.2. GPT

python3 GPT_eval_multi.py  \
--exp-name TEST_GPT \
--batch-size 128 \
--num-layers 9 \
--embed-dim-gpt 1024 \
--nb-code 512 \
--n-head-gpt 16 \
--block-size 51 \
--ff-rate 4 \
--drop-out-rate 0.1 \
--resume-pth output/VQVAE/net_last.pth \
--vq-name VQVAE \
--out-dir output \
--total-iter 300000 \
--lr-scheduler 150000 \
--lr 0.0001 \
--dataname t2m \
--down-t 2 \
--depth 3 \
--quantizer ema_reset \
--eval-iter 10000 \
--pkeep 0.5 \
--dilation-growth-rate 3 \
--vq-act relu \
--resume-trans output/GPT/net_best_fid.pth

6. SMPL Mesh Rendering

python3 render_final.py --filedir output/TEST_GPT/ --motion-list 000019 005485

7. Acknowledgement

We appreciate helps from :

• public code like text-to-motion, TM2T, MDM, MotionDiffuse etc.
• Mathis Petrovich, Yuming Du, Yingyi Chen, Dexiong Chen and Xuelin Chen for inspiring discussions and valuable feedback.
• Minh Chien Vu for the hugging face space demo.

8. ChangLog

• 2023/02/19 add the hugging face space demo for both skelton and SMPL mesh visualization.