Page 1 of 1

Extracting from Multiple Sources

Posted: Sat Mar 20, 2021 12:43 am
by SupremeEggplant

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?


Re: Extracting from Multiple Sources

Posted: Sat Mar 20, 2021 1:34 pm
by torzdf

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.