---
title: LAM-20K
canonical_url: "https://www.modelscope.cn/models/Damo_XR_Lab/LAM-20K"
md_url: "https://www.modelscope.cn/models/Damo_XR_Lab/LAM-20K.md"
repository: Damo_XR_Lab/LAM-20K
chinese_name: "LAM-20K模型"
last_updated: 2025-04-23
license: "Apache License 2.0"
pipeline_tag: face-reconstruction
tasks:
  - face-reconstruction
parameters: 588.8M
tensor_type:
  - F32
  - I64
library_name:
  - safetensors
  - pytorch
frameworks:
  - Pytorch
downloads: 1627
stars: 3
---

# LAM-20K

> LAM-20K - Damo_XR_Lab 在 ModelScope 开源的模型。LAM-20K预训练模型：https://aigc3d.github.io/projects/LAM/

Damo_XR_Lab/LAM-20K 是 ModelScope 魔搭社区上的 588.8M 参数face-reconstruction模型，采用 Apache License 2.0 许可。

- **Repository**: Damo_XR_Lab/LAM-20K
- **License**: Apache License 2.0
- **Tasks**: face-reconstruction
- **Parameters**: 588.8M
- **Downloads**: 1627
- **Stars**: 3
- **Last updated**: 2025-04-23

Source: https://www.modelscope.cn/models/Damo_XR_Lab/LAM-20K

---

# LAM: Large Avatar Model for One-shot Animatable Gaussian Head 

[![Website](https://raw.githubusercontent.com/prs-eth/Marigold/main/doc/badges/badge-website.svg)](https://aigc3d.github.io/projects/LAM/) 
[![arXiv Paper](https://img.shields.io/badge/📜-arXiv:2503-10625)](https://arxiv.org/pdf/2502.17796)
[![HuggingFace](https://img.shields.io/badge/🤗-HuggingFace_Space-blue)](https://huggingface.co/spaces/3DAIGC/LAM)
[![ModelScope](https://img.shields.io/badge/%20ModelScope%20-Space-blue)](https://www.modelscope.cn/studios/Damo_XR_Lab/LAM_Large_Avatar_Model) 
[![Apache License](https://img.shields.io/badge/📃-Apache--2.0-929292)](https://www.apache.org/licenses/LICENSE-2.0)

### <p align="center"> LAM: Large Avatar Model for One-shot Animatable Gaussian Head </p>

#####  <p align="center"> Yisheng He*, Xiaodong Gu*, Xiaodan Ye, Chao Xu, Zhengyi Zhao, Yuan Dong†, Weihao Yuan†, Zilong Dong, Liefeng Bo </p>

#####  <p align="center"> Tongyi Lab, Alibaba Group</p>

####  <p align="center"> **"Build 3D Interactive Chatting Avatar with One Image in Seconds!"** </p>



### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型

#### SDK下载
```bash
#安装ModelScope
pip install modelscope
```
bash命令
```bash
modelscope download "Damo_XR_Lab/LAM-20K" --local_dir "./model_zoo/lam_models/releases/lam/lam-20k/step_045500/"
```
或者使用python
```python
#SDK模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('Damo_XR_Lab/LAM-20K')
```

#### Git下载
```
#Git模型下载
git clone https://www.modelscope.cn/Damo_XR_Lab/LAM-20K.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>