- Python: python 3.10.6 (added to path)
- Desktop Development with C++: This can be installed via Visual Studio Installer to ensure compatibility with the necessary packages.
- Microsoft Visual C++ Redistributable: Download and install the Microsoft Visual C++ Redistributable from the link below:
- Microsoft Visual C++ Redistributable (x64)
- ffmpeg (added to path)
- at this moment i'm using torch 2.6.0 (with cuda 12.6 and cudnn inside)
-
Install Desktop Development with C++
- Open Visual Studio Installer.
- Install the Desktop Development with C++ workload to ensure compatibility with the required C++ components for packages like ONNX and InsightFace.
- git clone https://github.com/DJHanceNL/Future-Roop.git
- cd Future-Roop
- python -m venv env
- env\Scripts\activate
- python.exe -m pip install --upgrade pip
- python -m pip install -r requirements.txt
- python run.py
backup model folder
- Platform-independant Browser GUI
- Selection of multiple input/output faces in one go
- Many different swapping modes, first detected, face selections, by gender
- Batch processing of images/videos
- Masking of face occluders using text prompts or automatically
- Optional Face Upscaler/Restoration using different enhancers
- Preview swapping from different video frames
- Live Fake Cam using your webcam
- Extras Tab for cutting videos etc.
- Settings - storing configuration for next session
- Theme Support
and lots more...
This project is for technical and academic use only. Users of this software are expected to use this software responsibly while abiding the local law. If a face of a real person is being used, users are suggested to get consent from the concerned person and clearly mention that it is a deepfake when posting content online. Developers of this software will not be responsible for actions of end-users. Please do not apply it to illegal and unethical scenarios.
In the event of violation of the legal and ethical requirements of the user's country or region, this code repository is exempt from liability
03.02.2025 v0.0.3
Just the original
Lots of ideas, code or pre-trained models borrowed