---
title: VimoRAG
canonical_url: "https://www.modelscope.cn/models/Walkerhai/VimoRAG"
md_url: "https://www.modelscope.cn/models/Walkerhai/VimoRAG.md"
repository: Walkerhai/VimoRAG
last_updated: 2025-11-29
parameters: 402.7M
tensor_type:
  - BF16
library_name:
  - safetensors
downloads: 24
stars: 0
---

# VimoRAG

> VimoRAG - Walkerhai 在 ModelScope 开源的模型。--- license: Apache License 2.0 tags: [motion generation, retrieval augmented generation, motion LLM]

- **Repository**: Walkerhai/VimoRAG
- **Parameters**: 402.7M
- **Downloads**: 24
- **Stars**: 0
- **Last updated**: 2025-11-29

Source: https://www.modelscope.cn/models/Walkerhai/VimoRAG

---

---
license: Apache License 2.0
tags: [motion generation, retrieval augmented generation, motion LLM]


# VimoRAG: Video-based Retrieval-augmented 3D Motion Generation for Motion Language Models

This repository contains the datasets and models for [VimoRAG: Video-based Retrieval-augmented 3D Motion Generation for Motion Language Models](https://arxiv.org/abs/2508.12081).

VimoRAG introduces a novel video-based retrieval-augmented motion generation framework for motion large language models (LLMs). It leverages large-scale in-the-wild video databases to enhance 3D motion generation by retrieving relevant 2D human motion signals.

Project Page: [https://walkermitty.github.io/VimoRAG/](https://walkermitty.github.io/VimoRAG/)
Code: [https://github.com/WalkerMitty/VimoRAG](https://github.com/WalkerMitty/VimoRAG)



SDK下载
```bash
#安装ModelScope
pip install modelscope
```
```python
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('Walkerhai/VimoRAG')
```
Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/Walkerhai/VimoRAG.git
```

<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>