{"id":376,"date":"2022-08-30T08:47:27","date_gmt":"2022-08-30T08:47:27","guid":{"rendered":"https:\/\/formatswap.com\/blog\/?p=376"},"modified":"2023-02-04T09:50:01","modified_gmt":"2023-02-04T09:50:01","slug":"how-to-create-a-deepfake-video-using-deepfacelab","status":"publish","type":"post","link":"https:\/\/formatswap.com\/blog\/machine-learning-tutorials\/how-to-create-a-deepfake-video-using-deepfacelab\/","title":{"rendered":"How to Create a Deepfake Video Using DeepFaceLab"},"content":{"rendered":"\n
\"deep<\/figure>\n\n\n\n

In this tutorial you will learn how to create a deepfake<\/a> video using DeepFaceLab<\/a>. This application uses machine learning to swap almost any face from a video for one that you choose. DeepFaceLab<\/a> is currently the best software by far for making deepfakes<\/a>. In this tutorial we will be using the Windows 10<\/a> operating system. However the steps are pretty much the same if you are using Linux. So you should be able to utilize this tutorial with either operating system. It is advised that you have a powerful GPU such as a Nvidia GTX 1060<\/a> or better for creating deepfakes<\/a>. If you want the best experience possible I would recommend you use a RTX 3080<\/a> or RTX 3090<\/a> graphics card. The software will still work with a low end GPU, but it could take multiple weeks to train your model. Having a high end GPU will also allow you to render the face swaps in a higher resolution. To learn how to create a deepfake continue reading below.<\/p>\n\n\n\n

Download DeepFaceLab<\/h2>\n\n\n\n

The first step is to download the latest version of DeepFaceLab<\/a>. You can do so by going to the DeepFaceLab Github<\/a> page and scrolling down to releases. Click on the Windows (Mega.nz)<\/a> link to download the correct release for your graphics card. If you are installing in Linux you will have to follow the instructions provided on the Linux (github)<\/a> page.<\/p>\n\n\n\n

\"deepfacelab<\/figure>\n\n\n\n

Choose Version<\/h2>\n\n\n\n

After navigating to the Mega.nz download link you will need to select a version of DeepFaceLab. This is based on which graphics card you have installed. In this tutorial I am using a GTX 1080 so I will download “DeepFaceLab_NVIDIA_up_to_RTX2080Ti_build_11_20_2021.exe”. Choose the version that is correct for your system.<\/p>\n\n\n\n

\"deepfacelab<\/figure>\n\n\n\n

Open the Workspace<\/h2>\n\n\n\n

After downloading the application, extract the zip file and open the folder. Your folder should look similar to this.<\/p>\n\n\n\n

\"open<\/figure>\n\n\n\n

Collect source videos<\/h2>\n\n\n\n

This is by far the most important step of getting a good result from the process. You need to select a video of your source (persons face you want to copy). As well as a destination video (where you want your source face copied to). You want to find a clip for each that is 5-10 minutes long with multiple angles of the faces. A good source for these videos are interviews on YouTube. Below are the two videos I am going to use. After you download the videos rename the source video to “data_src.mp4”<\/strong> and the destination video to “data_dst.mp4”<\/strong>. Then move both MP4 files into the “workspace”<\/strong> folder.<\/p>\n\n\n\n

Source face:<\/strong><\/p>\n\n\n\n

\n