KYC Software

Installation guide to run deepfakes on Windows applications like Zoom or verification software.

GUI Installation: 1. Download and run the executable for your OS: https://drive.google.com/file/d/1nL3WkntTrVBZVQvOF2i7clY8eFRqSr8L/view 1.1 Download dot.zip, unzip it, and run dot.exe.

How to Use the GUI: 1. Put the original picture into the “source” section. 2. Write the camera ID number in the “target” box. In most cases, 0 is correct. 3. Write the config file in the ‘config_file’ section. Pick a default set you from the dropdown list or use your own file. 4. Check the ‘use_gpu’ box if you want to use the GPU, but this is completely optional. 5. Click the ‘RUN’ button to start the deepfake.

CLI Installation: 1. Install Prerequisites Windows: a) Download and install Visual Studio Community. b) Install Desktop development with C++ from the Visual Studio Installer. c) Create Conda Enviroment. d) The instructions assume you have Minicond installed on your machine. If noted you need to install it.

2. With GPU Support:

conda env create -f envs/environment-gpu.yaml

conda activate dot

Install torch and torchvision dependencies based on the CUDA version installed on your machine: Install CUDA 11.8

Install cudatoolkit from conda:

conda install cudatoolkit=<cuda_version_no>  # Replace <cuda_version_no> with the version on your machine (e.g., 12.4)

Install torch and torchvision dependencies:

pip install torch==2.4.1+<cuda_tag> torchvision==0.19.1+<cuda_tag> torchaudio==2.4.1 --index-url https://download.pytorch.org/whl/cu124

Where is the CUDA tag defined by PyTorch. For example:

pip install torch==2.4.1+cu124 torchvision==0.19.1+cu124 torchaudio==2.4.1 --index-url https://download.pytorch.org/whl/cu124

for CUDA 12.4.

Note: torch1.9.0+cu111 can also be used. To check that torch and torchvision are installed correctly, run:

python -c "import torch; print(torch.cuda.is_available())"

If the output is True, the dependencies are installed with CUDA support.

SimSwap

dot -c ./configs/simswap.yaml --target 0 --source "./data" --use_gpu

SimSwapHQ

dot -c ./configs/simswaphq.yaml --target 0 --source "./data" --use_gpu

FOMM

dot -c ./configs/fomm.yaml --target 0 --source "./data" --use_gpu

FaceSwap CV2

dot -c ./configs/faceswap_cv2.yaml --target 0 --source "./data" --use_gpu

Note: To enable face superresolution, use the flag

--gpen_type gpen_256 or --gpen_type gpen_512

Docker

What is a Docker? A tool that lets you run apps or programs in “containers.” The containers are like mini computers that contain everything the app needs to run.

Getting your webcam to work inside Docker containers: https://medium.com/@jijupax/connect-the-webcam-to-docker-on-mac-or-windows-51d894c44468

- Setting up Docker. - Build the container.

docker-compose up --build -d

- Access the container.

docker-compose exec dot "/bin/bash"

- Connect Docker to the webcam.

Windows: Follow the instructions under Windows to set up the webcam with Docker.

- Build the container.

docker build -t dot -f Dockerfile .

- Run the container.

docker run -ti --gpus all \
-e NVIDIA_DRIVER_CAPABILITIES=compute,utility \
-e NVIDIA_VISIBLE_DEVICES=all \
-e PYTHONUNBUFFERED=1 \
-e DISPLAY=192.168.99.1:0 \
-v .:/dot \
--runtime nvidia \
--entrypoint /bin/bash \
-p 8080:8080 \
--device=/dev/video0:/dev/video0 \
-v /tmp/.X11-unix:/tmp/.X11-unix \
dot

Virtual Camera Injection: Instructions vary depending on your operating system.

Windows: - Install OBS Studio. - Install VirtualCam Plugin. - Choose “Install and register only 1 virtual camera.” - Run OBS Studio. - In he Sources section, press the Add button (“+” sign.). - Select "Windows Capture" and press OK. In the appeared window, choose "[python.exe]: fomm" in the Window drop-down menu and press OK. Then select Edit -> Transform -> Fit to screen. - In OBS Studio, go to Tools -> VirtualCam. Check AutoStart. - Set Buffered Frames to 0 and press Start. - Now OBS-Camera camera should be available in Zoom (or other videoconferencing software).