---
title: LAM-A2E
canonical_url: "https://www.modelscope.cn/studios/Damo_XR_Lab/LAM-A2E"
md_url: "https://www.modelscope.cn/studios/Damo_XR_Lab/LAM-A2E.md"
repository: Damo_XR_Lab/LAM-A2E
chinese_name: "语音驱动单张照片人脸重建模型"
last_updated: 2025-04-21
sdk_type: gradio
sdk_version: 5.12.0
downloads: 0
stars: 17
---

# LAM-A2E

> LAM-A2E - Damo_XR_Lab 在 ModelScope 创建的在线 Demo。LAM-A2E: Audio to Expression

Damo_XR_Lab/LAM-A2E 是 ModelScope 魔搭社区上的在线可交互 Demo（创空间），基于 gradio 5.12.0 构建，中文名为「语音驱动单张照片人脸重建模型」。

- **Repository**: Damo_XR_Lab/LAM-A2E
- **SDK**: gradio
- **SDK version**: 5.12.0
- **Downloads**: 0
- **Stars**: 17
- **Last updated**: 2025-04-21

Source: https://www.modelscope.cn/studios/Damo_XR_Lab/LAM-A2E

---

# LAM-A2E: Audio to Expression

[![Website](https://raw.githubusercontent.com/prs-eth/Marigold/main/doc/badges/badge-website.svg)](https://aigc3d.github.io/projects/LAM/) 
[![Apache License](https://img.shields.io/badge/📃-Apache--2.0-929292)](https://www.apache.org/licenses/LICENSE-2.0)

#### This project leverages audio input to generate ARKit blendshapes-driven facial expressions in ⚡real-time⚡, powering ultra-realistic 3D avatars generated by [LAM](https://github.com/aigc3d/LAM).

## Demo

<div align="center">
  <video controls src="https://github.com/user-attachments/assets/a89a0d70-a573-4d61-91bd-4f09a0b6ce2c">
  </video>
</div>

## 📢 News


### To do list
- [ ] Release Huggingface space.
- [ ] Release Modelscope space.
- [ ] Release the LAM-A2E model based on the Flame expression.
- [ ] Release Interactive Chatting Avatar SDK with [OpenAvatarChat](https://github.com/HumanAIGC-Engineering/OpenAvatarChat), including LLM, ASR, TTS, LAM-Avatars.



## 🚀 Get Started
### Environment Setup
```bash
git clone git@github.com:aigc3d/LAM_Audio2Expression.git
cd LAM_Audio2Expression
# Create conda environment (currently only supports Python 3.10)
conda create -n lam_a2e python=3.10
# Activate the conda environment
conda activate lam_a2e
# Install with Cuda 12.1
sh  ./scripts/install/install_cu121.sh
# Or Install with Cuda 11.8
sh ./scripts/install/install_cu118.sh
```


### Download

```
# HuggingFace download
# Download Assets and Model Weights
huggingface-cli download 3DAIGC/LAM_audio2exp --local-dir ./
tar -xzvf LAM_audio2exp_assets.tar && rm -f LAM_audio2exp_assets.tar
tar -xzvf LAM_audio2exp_streaming.tar && rm -f LAM_audio2exp_streaming.tar

# Or OSS Download (In case of HuggingFace download failing)
# Download Assets
wget https://virutalbuy-public.oss-cn-hangzhou.aliyuncs.com/share/aigc3d/data/LAM/LAM_audio2exp_assets.tar
tar -xzvf LAM_audio2exp_assets.tar && rm -f LAM_audio2exp_assets.tar
# Download Model Weights
wget https://virutalbuy-public.oss-cn-hangzhou.aliyuncs.com/share/aigc3d/data/LAM/LAM_audio2exp_streaming.tar
tar -xzvf LAM_audio2exp_streaming.tar && rm -f LAM_audio2exp_streaming.tar

Or Modelscope Download
git clone https://www.modelscope.cn/Damo_XR_Lab/LAM_audio2exp.git ./modelscope_download
```


### Quick Start Guide
#### Using <a href="https://github.com/gradio-app/gradio">Gradio</a> Interface: 
We provide a simple Gradio demo with **WebGL Render**, and you can get rendering results by uploading audio in seconds.

<img src="./assets/images/snapshot.png" alt="teaser" width="1000"/>



```
python app_lam_audio2exp.py
```

### Inference
```bash
# example: python inference.py --config-file configs/lam_audio2exp_config_streaming.py --options save_path=exp/audio2exp weight=pretrained_models/lam_audio2exp_streaming.tar audio_input=./assets/sample_audio/BarackObama_english.wav
python inference.py --config-file ${CONFIG_PATH} --options save_path=${SAVE_PATH} weight=${CHECKPOINT_PATH} audio_input=${AUDIO_INPUT}
```

### Acknowledgement
This work is built on many amazing research works and open-source projects:
- [FLAME](https://flame.is.tue.mpg.de)
- [FaceFormer](https://github.com/EvelynFan/FaceFormer)
- [Meshtalk](https://github.com/facebookresearch/meshtalk)
- [Unitalker](https://github.com/X-niper/UniTalker)
- [Pointcept](https://github.com/Pointcept/Pointcept)

Thanks for their excellent works and great contribution.


### Related Works
Welcome to follow our other interesting works:
- [LAM](https://github.com/aigc3d/LAM)
- [LHM](https://github.com/aigc3d/LHM)


### Citation
```
@inproceedings{he2025LAM,
  title={LAM: Large Avatar Model for One-shot Animatable Gaussian Head},
  author={
    Yisheng He and Xiaodong Gu and Xiaodan Ye and Chao Xu and Zhengyi Zhao and Yuan Dong and Weihao Yuan and Zilong Dong and Liefeng Bo
  },
  booktitle={arXiv preprint arXiv:2502.17796},
  year={2025}
}
```