
TVPaint Animation
The digital solution for your professional 2D animation projects.

Generate realistic 3D motion coefficients for stylized audio-driven single image talking face animation.

SadTalker is an open-source project focused on generating realistic talking face animations from a single portrait image and an audio file. It leverages 3D motion coefficients to drive the animation, enabling stylized and realistic facial movements synchronized with the provided audio. The core architecture involves extracting audio features, predicting 3D motion coefficients, and rendering the talking face video. The project offers a WebUI extension, a Gradio demo, and CLI usage for animating portrait images. It supports full image animation and provides options for enhancing the quality of the generated video using GFPGAN. The tool can be integrated into Discord and has a Stable Diffusion WebUI extension, expanding its use cases for content creation and communication. The project is built on Python, PyTorch, and other open-source libraries.
SadTalker is an open-source project focused on generating realistic talking face animations from a single portrait image and an audio file.
Explore all tools that specialize in facial expression synthesis. This domain focus ensures SadTalker delivers optimized results for this specific requirement.
Utilizes pre-trained models to predict realistic 3D motion coefficients from audio inputs, enabling nuanced facial movements.
Integrates with GFPGAN to enhance the quality of generated faces, reducing artifacts and improving visual fidelity.
Provides a user-friendly WebUI extension for easy access and configuration of SadTalker features.
Supports animation of full images, allowing for more natural and expressive body language in addition to facial movements.
Allows integration with Stable Diffusion WebUI, enabling the generation of talking face animations from text prompts.
Install Anaconda, Python 3.8, and git.
Clone the SadTalker repository: `git clone https://github.com/OpenTalker/SadTalker.git`
Navigate to the SadTalker directory: `cd SadTalker`
Create a conda environment: `conda create -n sadtalker python=3.8`
Activate the conda environment: `conda activate sadtalker`
Install PyTorch: `pip install torch==1.12.1+cu113 torchvision==0.13.1+cu113 torchaudio==0.12.1 --extra-index-url https://download.pytorch.org/whl/cu113`
Install ffmpeg: `conda install ffmpeg`
Install the remaining requirements: `pip install -r requirements.txt`
Download the necessary pre-trained models using `bash scripts/download_models.sh`
Run the WebUI demo using `bash webui.sh` or `python app_sadtalker.py`
All Set
Ready to go
Verified feedback from other users.
"Users praise the tool's realism and ease of use, but some report occasional synchronization issues."
Post questions, share tips, and help other users.

The digital solution for your professional 2D animation projects.

Empowering independent artists with digital music distribution, publishing administration, and promotional tools.

Convert creative micro-blogs into high-performance web presences using generative AI and Automattic's core infrastructure.

Fashion design technology software and machinery for apparel product development.

Instantly turns any text to natural sounding speech for listening online or generating downloadable audio.

Professional studio-quality AI headshot generator for individuals and teams.