Roop-FaceSwap

Requirements

• Python 3.10.0rc2 (or 3.10.x)
• CUDA Toolkit (must be compatible with your GPU and TensorFlow)
• cuDNN (extract into your CUDA installation path)

Verifying CUDA and cuDNN Installation

To verify that CUDA is installed correctly, run the following in Command Prompt or PowerShell:

nvcc --version
This should return the version of the CUDA compiler. If it says 'nvcc' is not recognized, make sure the CUDA bin directory is added to your system PATH (e.g., C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.0\bin).

For cuDNN, ensure the following cuDNN files are copied into your CUDA folder:

bin\cudnn*.dll → into CUDA_PATH\bin

include\cudnn*.h → into CUDA_PATH\include

lib\x64\cudnn*.lib → into CUDA_PATH\lib\x64

Setup Instructions

1. Create and Activate the Virtual Environment

Set-ExecutionPolicy -Scope CurrentUser -ExecutionPolicy RemoteSigned
& "C:\Users\YourUsername\AppData\Local\Programs\Python\Python310\python.exe" -m venv onnx-env
. .\onnx-env\Scripts\Activate.ps1

pip install -r requirements.txt

Or run:

• install_requirements.bat

  pip install torch torchvision
  

. .\onnx-env\Scripts\Activate.ps1 onnx-env\Scripts\activate.bat source onnx-env/Scripts/activate

Run main.py

Using Python directly:

python run.py

Using provided scripts:

Windows:

• .\run.bat or
• .\run.ps1

Unix-like systems (Linux/macOS):

• .\run.sh

  
  

Python Requirements:

--extra-index-url https://download.pytorch.org/whl/cu118

numpy==1.24.3
opencv-python==4.8.0.74
onnx==1.14.0
insightface==0.7.3
psutil==5.9.5
tk==0.1.0
customtkinter==5.2.0
tkinterdnd2==0.3.0; sys_platform != 'darwin' and platform_machine != 'arm64'
tkinterdnd2-universal==1.7.3; sys_platform == 'darwin' and platform_machine == 'arm64'
pillow==10.0.0
onnxruntime==1.15.1; python_version != '3.9' and sys_platform == 'darwin' and platform_machine != 'arm64'
onnxruntime-coreml==1.13.1; python_version == '3.9' and sys_platform == 'darwin' and platform_machine != 'arm64'
onnxruntime-silicon==1.13.1; sys_platform == 'darwin' and platform_machine == 'arm64'
onnxruntime-gpu==1.15.1; sys_platform != 'darwin'
tensorflow==2.13.0
opennsfw2==0.10.2
protobuf==4.23.4
tqdm==4.65.0
gfpgan==1.3.8

Installation

Basic - It is more likely to work on your computer, but will be quite slow

Acceleration - Unleash the full potential of your CPU and GPU

Usage

Start the program with arguments:

python run.py [options]

-h, --help                                                                 show this help message and exit
-s SOURCE_PATH, --source SOURCE_PATH                                       select an source image
-t TARGET_PATH, --target TARGET_PATH                                       select an target image or video
-o OUTPUT_PATH, --output OUTPUT_PATH                                       select output file or directory
--frame-processor FRAME_PROCESSOR [FRAME_PROCESSOR ...]                    frame processors (choices: face_swapper, face_enhancer, ...)
--keep-fps                                                                 keep target fps
--keep-frames                                                              keep temporary frames
--skip-audio                                                               skip target audio
--many-faces                                                               process every face
--reference-face-position REFERENCE_FACE_POSITION                          position of the reference face
--reference-frame-number REFERENCE_FRAME_NUMBER                            number of the reference frame
--similar-face-distance SIMILAR_FACE_DISTANCE                              face distance used for recognition
--temp-frame-format {jpg,png}                                              image format used for frame extraction
--temp-frame-quality [0-100]                                               image quality used for frame extraction
--output-video-encoder {libx264,libx265,libvpx-vp9,h264_nvenc,hevc_nvenc}  encoder used for the output video
--output-video-quality [0-100]                                             quality used for the output video
--max-memory MAX_MEMORY                                                    maximum amount of RAM in GB
--execution-provider {cpu} [{cpu} ...]                                     available execution provider (choices: cpu, ...)
--execution-threads EXECUTION_THREADS                                      number of execution threads
-v, --version                                                              show program's version number and exit

Headless

Using the -s/--source, -t/--target and -o/--output argument will run the program in headless mode.

© Cursed Entertainment