storyteller-ml/animation/SadTalker/docs/install.md at 45a50d2dbaa35ed79f53afa10b0023ea3cd89a09 - storyteller-ml - Gitea: Git with a cup of tea

storytold/storyteller-ml

mirror of https://github.com/storytold/storyteller-ml.git synced 2026-10-16 00:13:07 +00:00

Files

T

Brandon Thomas 2d2b25d5a6 Add SadTalker @ ae0b26359d44c9379450a8e02a38b45eeec15549

MIT license

Commit:

https://github.com/OpenTalker/SadTalker

commit ae0b26359d44c9379450a8e02a38b45eeec15549 (HEAD -> main, origin/main, origin/HEAD)
Author: shadowcun <shadowcun@tencent.com>
Date:   Mon Jul 3 13:48:35 2023 +0800

    fixed bug: hacking facexlib of FAN

2023-07-27 15:00:20 -04:00

1.2 KiB

Raw Blame History

Mac (Tested on M1 Mac OS 13.3)

git clone https://github.com/Winfredy/SadTalker.git

cd SadTalker 

conda create -n sadtalker python=3.8

conda activate sadtalker

# install pytorch 2.0
pip install torch torchvision torchaudio

conda install ffmpeg

pip install -r requirements.txt

pip install dlib # mac need to install the original dlib.

Windows Native

Make sure you have ffmpeg in the %PATH% as suggested in #54, following this installation to install ffmpeg.

Windows WSL

Make sure the environment: export LD_LIBRARY_PATH=/usr/lib/wsl/lib:$LD_LIBRARY_PATH

Docker installnation

A dockerfile are also provided by @thegenerativegeneration in docker hub, which can be used directly as:

docker run --gpus "all" --rm -v $(pwd):/host_dir wawa9000/sadtalker \
    --driven_audio /host_dir/deyu.wav \
    --source_image /host_dir/image.jpg \
    --expression_scale 1.0 \
    --still \
    --result_dir /host_dir