I cannot find a clear and easy to understand answer on this. As said in the guide it is best to have multiple sources to extract from, however, they will not be from the same video. This will generate multiple folders with datasets and multiple alignment files. Should I simply train each dataset from each source onto what I want to swap or is there a way to combine all the datasets into without combining all the sources into one video prior to extraction?
Want to know about the Faceswap's Face Extraction process? Got tips, ideas or just want to learn about how it all works? Then this is the place for you
This forum is for discussing tips and understanding the process involved for Extracting and preparing face sets for training a model in Faceswap.
If you have found a bug are having issues with the Extraction process not working, then you should post in the Extract Support forum.
Please mark any answers that fixed your problems so others can find the solutions.
For training, it is as simple as extracting the faces you want from numerous sources, then putting the final result all into one folder and training on it.
My word is final