| --- |
| license: other |
| license_name: cc-by-nc-4.0-and-amass |
| license_link: https://amass.is.tue.mpg.de/license.html |
| pipeline_tag: robotics |
| tags: |
| - humanoid-control |
| - physics-based-animation |
| - diffusion-policy |
| - flow-matching |
| - text-to-motion |
| - isaac-gym |
| extra_gated_prompt: >- |
| The data and the weights are derived from AMASS and HumanML3D. To access them, you must have registered at |
| https://amass.is.tue.mpg.de and accepted the AMASS license, and you may use them for non-commercial scientific |
| research only. |
| extra_gated_fields: |
| Name: text |
| Affiliation: text |
| I have registered on the AMASS website and accept the AMASS license: checkbox |
| I will use these files for non-commercial research only: checkbox |
| --- |
| |
| # SCRIPT |
|
|
| Weights and data of **SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven |
| Physics-Based Humanoid Control** (SIGGRAPH Asia 2026). |
|
|
| [Paper](https://arxiv.org/abs/2605.22894) · [Project page](https://zhanglele12138.github.io/SCRIPT/) · |
| [Code](https://github.com/zhanglele12138/SCRIPT-codes) · [Video](https://youtu.be/Q9RLbCHr7Gw) |
|
|
| ## Files |
|
|
| | Path | Size | Contents | |
| |---|---|---| |
| | `checkpoints/stage1_humanml3d_0.5B/` | 1.9 GB | Stage I policy (0.5B, step 80k, EMA weights), with its normaliser, null text and scheduler | |
| | `checkpoints/evaluators/humanml3d_paper/` | 0.3 GB | the text-motion evaluator of the paper | |
| | `checkpoints/evaluators/humanml3d_retrained/` | 0.3 GB | the evaluator retrained with the released code | |
| | `data/humanml3d/window_154+4/` | 52 GB | tracked training and validation trajectories with CLIP text features, the index of training windows, the normaliser | |
| | `data/humanml3d/evaluate_data/test.h5` | 9.1 GB | the 11,468 tracked test trajectories: the ground truth of the evaluation | |
| | `data/humanml3d/test_motions/` | 4.5 GB | the test set in 8 shards, for the standing start and for the start from the reference motion | |
| | `data/humanml3d/texts.tar.gz` | 18 MB | the captions | |
| | `data/humanml3d/null_text.pt` | 0.4 MB | the CLIP features of the empty caption, for classifier-free guidance in training | |
|
|
| ## Usage |
|
|
| Accept the conditions on this page, log in with `hf auth login`, and download into the root of the |
| [code](https://github.com/zhanglele12138/SCRIPT-codes): |
|
|
| ```bash |
| hf download Zhanglele/SCRIPT --local-dir . # everything (68 GB) |
| hf download Zhanglele/SCRIPT --include "checkpoints/*" --local-dir . # only the weights (2.5 GB) |
| tar -xzf data/humanml3d/texts.tar.gz -C data/humanml3d |
| ``` |
|
|
| The files are then where the code's configs and commands expect them, e.g. |
|
|
| ```bash |
| bash scripts/eval_humanml3d.sh checkpoints/stage1_humanml3d_0.5B checkpoints/evaluators/humanml3d_paper --keep-copies |
| ``` |
|
|
| | Evaluator | MM_Dist ↓ | R@1 ↑ | R@2 ↑ | R@3 ↑ | FID ↓ | Diversity | |
| |---|---|---|---|---|---|---| |
| | `humanml3d_paper` (`--keep-copies`) | 2.020 | 0.484 | 0.650 | 0.738 | 0.137 | 1.460 | |
| | `humanml3d_retrained` | 1.784 | 0.494 | 0.661 | 0.754 | 0.127 | 1.352 | |
|
|
| ## License |
|
|
| The motions come from [AMASS](https://amass.is.tue.mpg.de) and HumanAct12, cut into captioned clips by |
| [HumanML3D](https://github.com/EricGuo5513/HumanML3D) and tracked in simulation with |
| [PHC](https://github.com/ZhengyiLuo/PHC); the data is subject to the |
| [AMASS license](https://amass.is.tue.mpg.de/license.html). The weights are released under |
| [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/). Both are for non-commercial research only. |
|
|
| ## Citation |
|
|
| ```bibtex |
| @article{zhang2026script, |
| title = {SCRIPT: Scalable Diffusion Policy with Multi-stage Training for |
| Language-driven Physics-Based Humanoid Control}, |
| author = {Zhang, Jingyan and Liang, Han and Zhang, Ruichi and Li, Bin and |
| Zhang, Juze and Chen, Xin and Wang, Jingya and Xu, Lan and Yu, Jingyi}, |
| journal = {arXiv preprint arXiv:2605.22894}, |
| year = {2026} |
| } |
| ``` |
|
|
