Facefusion has released another version – Facefusion 3.4.1. And here is how you can install the latest version on your Windows PC using Anaconda. For those who do not have Anaconda, please go to the Anaconda official website and download and install it to your PC. After this, go to the Facefusion GitHub page and download the Facefusion files and extract them.

Once this is done, open the Anaconda prompt and create the Python Environment for Facefusion 3.4.1. For that, type: conda create –name facefusion python=3.12 (note its double dash name). This will create a Python environment 3.12. Now let’s activate it by typing conda activate facefusion – you can see the base name has changed to facefusion.

Now open the Facefusion folder, copy the address (Control + C), and in Anaconda type cd followed by the address. Then type python install.py onnxruntime. You will find options such as Default, CUDA, OpenVINO, DirectML, CoreML, and ROCm. Choose the option as per your PC: CPU for processors, CUDA for NVIDIA, CoreML for macOS, DirectML for Windows GPUs, OpenVINO for Intel CPUs and GPUs, or ROCm for AMD. Since this PC is Intel without GPU, we will use OpenVINO: python install.py onnxruntime –OpenVINO (note its double dash name)

After running onnxruntime with OpenVINO, all dependencies will download so it will take some time. Then install FFmpeg by typing conda install ffmpeg. Now to run Facefusion, type python facefusion.py run. This will download some additional files, and the Facefusion app will run.

For those who do not want to go through all these steps, please download the Ready to Use Toolkit from the following link.

Hope this video was useful. Thank you very much.