relopyoung.blogg.se

Inside the workspace folder are 3 more folders that will hold the images and model files. The workspace folder is where all your deepfake data and files will be held. The internal folder includes the DeepFaceLab code and additional software and required libraries, such as CUDA, Python, and FFMpeg. You can think of these as individual tools, that you will use throughout the deepfake process. They are numbered in the general order that you should follow, and have names describing their purpose. The files in the main folder allow you to interact with the software. These are all the files and folders required to make a deepfake, including the DeepFaceLab code, additional packages and software, workspace folder, and some sample video data. Open the folder where you extracted DeepFaceLab. Now I’ll briefly go over the main components of the software. You can train for free in the cloud using Google Colab, however you will still need one of the desktop versions to prepare your files. There is also a version of DeepFaceLab for Google Colab. This version is no longer maintained, and many of the files and options will differ from the current builds.

If you are unable to run any of these builds you can try the DeepFaceLab 1.0 OpenCL build. Supported hardware includes AMD Radeon R5, R7, and R9 200 series or newer, Intel HD Graphics 500 series or newer, and NVIDIA G-Force GTX 900 series or newer.

The Direct X 12 build can be used with AMD, Intel, and NVIDIA devices with Direct X 12 running on Windows 10. An internet connection is temporarily required for this update. The file labeled ’10) make CPU only.bat’ will modify your software by installing an older version of TensorFlow. You can also train on a CPU with AVX instruction set. You can check your card on NVIDIA’s CUDA Compute Capability List:

The NVIDIA up to RTX 2080 TI build supports an NVIDIA GPU with CUDA 3.5 and higher. If you have one of these cards you need to use this build. The DeepFaceLab 2.0 NVIDIA RTX 3000 series build specifically supports (and requires) an NVIDIA 3000 series GPU. The available builds and their requirements may change as the software develops. I’ll start with the highest requirements and work down the list. There are several builds to choose from, depending on your system hardware.