README.md

metadata

title: SadTalker
emoji: 😭
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 3.50.2
app_file: app.py
pinned: false
license: mit

SadTalker: Audio-Driven Talking Face Animation

This Space demonstrates SadTalker, a system for generating realistic talking head videos from a single image and audio input.

Features

• 🎭 Single Image Animation: Animate any portrait image with audio
• 🎵 Audio-Driven: Synchronize facial movements with speech
• ⚙️ Customizable Settings: Adjust pose style, preprocessing, and enhancement options
• 🎨 Face Enhancement: Optional GFPGAN integration for improved quality

Usage

1. Upload an Image: Choose a portrait image (preferably with a clear, front-facing face)
2. Upload Audio: Provide an audio file with speech
3. Adjust Settings (optional):
   • Pose Style: Choose from 47 different pose styles (0-46)
   • Face Model Resolution: 256 or 512 (higher = better quality but slower)
   • Preprocess Type: How to handle the input image
   • Still Mode: Reduces head motion for a more static result
   • GFPGAN Enhancer: Improves face quality in the output
4. Generate: Click the "Generate Video" button and wait for processing

Tips for Best Results

• Use clear, well-lit portrait images
• Front-facing photos work best
• Audio should be clear with minimal background noise
• For more details, see the best practices guide

Credits

Paper: SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation (CVPR 2023)

Authors: Wenxuan Zhang, Xiaodong Cun, Xuan Wang, Yong Zhang, Xi Shen, Yu Guo, Ying Shan, Fei Wang

GitHub: OpenTalker/SadTalker

License

This project is licensed under the MIT License.