Spring Festival Wushu Robot Replication Model

Spring Festival Wushu Robot Replication Model

A bundle of data folders for rebuilding the Spring Festival wushu robot workflow, including the data directories that PromptHMR needs. For developers who want to reproduce that pipeline.

Made by Datawhale on Hugging Face. These notes are Mindket's, written from its model page and model card; the model's own files and license are on Hugging Face.

About

What it is: This repository from Datawhale gathers the resources needed to reproduce the Spring Festival wushu robot workflow. It holds the data directories that PromptHMR needs, packed as files you download.

It exists to share model resources and support a reproduction of the workflow. The card is short and written in Chinese, so it lists folder names and one licensing note rather than a full guide.

Who it suits: Developers and robotics hobbyists who read Chinese and want to repeat the workflow, and who already work with PromptHMR or similar human-motion tools.

Industry | Who uses it | How they use it | Example
Robotics | Robot developers | Rebuild the workflow behind the wushu robot demo | Setting up the data folders before a trial run
Computer vision | Researchers | Get the body models and example data in one place | Collecting the folders PromptHMR reads
Education | Students | Follow a Chinese community's reproduction of a known demo | Working through the pipeline step by step
Open-source communities | Maintainers | Share the resource files for a workflow | Mirroring the data directories for teammates

Anyone who wants a ready-to-run app can skip it, since this is a set of data resources, not a program.

Where to use it:

• A local project that runs the PromptHMR workflow, where the data folders are placed.
• Windows, macOS or Linux with Python, for downloading the files.

Use case | Who | What they get back
Workflow reproduction | Robot developers | The data folders the workflow needs in one download
Resource sharing | Community teams | One place to fetch the same files
Study | Students | Example data and models to inspect

How to set it up: You need Python and the Hugging Face tool to download the files.

• Python on Windows, macOS or Linux
• The huggingface_hub package
• A project that uses PromptHMR, which the card does not describe
• Disk space for the data folders, whose sizes the card does not give

1. Install the Hugging Face tool.
2. Download the repository.
3. Place the data folders where your workflow expects them.

pip install -U huggingface_hub
hf download Datawhale/spring-festival-wushu-robot-replication-model

How to use it: The card gives no run command. After downloading, you will find a data folder with these parts, which you use in your own reproduction of the workflow.

• body_models
• pretrain
• annotations
• examples
• wheels

Example: A developer downloads the repository and copies the data folder into the project that runs the PromptHMR workflow. The five sub-folders then sit next to the code that reads them. The card does not describe the run itself.

For newcomers and experts: If you are new, treat this as a box of supporting files, not a program. Download it, look through the five folders, and match each one to what your workflow asks for.

For experts, the repository is a distribution point for the data PromptHMR depends on, including body models, pretrained files, annotations, examples and wheels. It does not document usage, so check the upstream projects for how the pieces fit together.

Download the repository from Hugging Face
Open the data folder
Copy body models and pretrained files into your project
Add annotations, examples and wheels
Run the workflow the way upstream describes

Good to know: The points below cover limits and costs.

• Documentation: the card is short and written in Chinese, with no run steps.
• License: Apache 2.0, and the card asks you to also follow the license terms of upstream dependencies such as SMPL and SMPL-X.
• Cost to run: none named.
• Data it reaches: it holds files you download and reads nothing else. It names no account or web service.
• Not for: use that ignores the upstream license terms, or anyone expecting a finished application.

On Hugging Face, 13 November 2026

• Library: none
• Downloads in the last 30 days: 0
• Likes: 4
• License: apache-2.0
• Tags: none

Links

• Model: https://huggingface.co/Datawhale/spring-festival-wushu-robot-replication-model
• Files: https://huggingface.co/Datawhale/spring-festival-wushu-robot-replication-model/tree/main

Get the model

Download its files with Hugging Face's command line:

pip install -U huggingface_hub
hf download Datawhale/spring-festival-wushu-robot-replication-model

Then follow the usage in its model card. Nothing in this kit runs by itself.