# Requirements : Nvidia GPU card & and Cuda tool kit install

# I am using this card : https://amzn.to/3mTa7HX

# Working Anaconda enviroment

# Git hub link

https://github.com/kwea123/VTuber_Unity

==============================

build the Python enviroment

=============================

conda create -n vtuber python=3.6

conda activate vtuber

Install Pytorch

https://pytorch.org/

====================

# how to find my Cuda version

nvcc --version

conda install pytorch torchvision torchaudio cudatoolkit=11.1 -c pytorch -c conda-forge

# download the github repository

git clone https://github.com/kwea123/VTuber_Unity.git

cd VTuber_Unity

pip install -r requirements_cpu.txt

Install DLIB

============

https://github.com/kwea123/VTuber_Unity/wiki/Dlib-installation-on-Windows

Install camke from here : https://cmake.org/download/

* First make sure Visual Studio (>2015) is installed and updated to the latest version.

* Try pip install dlib. If it fails, do the next step.

* Go to some directory and do git clone https://github.com/davisking/dlib.git.

* cd dlib and mkdir build and cd build.

* cmake .. -G "Visual Studio 16 2019" -T host=x64. Replace the year with your Visual Studio year.

* After the build complete (assuming no errors), mkdir lib.win-amd64-3.6 inside the build folder.

* cd .. then python setup.py install.

* Dlib should be successfully installed.

--------------------------------------------------------------------------

git clone https://github.com/kwea123/VTuber_Unity.git

cd VTuber_Unity

download the model.zip from this link: https://github.com/kwea123/VTuber_Unity/releases/tag/v1.0

You need to download the models here, extract and put into face_alignment/ckpts.

Test the install using the camera

=================================

python demo.py --debug --cpu

# connect to character

#download the character from this link : https://github.com/kwea123/VTuber_Unity/releases/tag/v1.0

python demo.py --connect --debug --cpu