Faceswap Forum

Can someone post some pictures of swaps when they consider training complete and the swapped results actually turn out decent? I would like some sort of reference for when to stop. (Does the blurriness ever go away completely? And is there a way to tweak a model with 300k iterations to get it to sharpen up?)

This is a really hard question to answer, as there are so many factors involved (data source/variety, model used, batch size, hardware etc).

However, there are examples on our Discord server. This is an example of a trained model (of probably more complexity/resolution that the one you will be training)

Balmmaker wrote: ↑Sat Jan 01, 2022 8:09 pm

Can someone post some pictures of swaps when they consider training complete and the swapped results actually turn out decent? I would like some sort of reference for when to stop. (Does the blurriness ever go away completely? And is there a way to tweak a model with 300k iterations to get it to sharpen up?)

Good question that is hard to answer.
viewtopic.php?f=27&t=922

I reduce the batch size , and check the "no warp" for another 10K iterations, then see how it looks.
There are other things you can do as well, scattered throughout this forum, for tips and tricks people learn.