Faceswap Forum

I have recently re-installed Windows and Facewap on my computer (No, I have not made any hardware changes regarding GPU or CPU), and now all of old models refuse to train, nor will loading weights from existing models into new models, giving the error: TypeError: __init__() got an unexpected keyword...

The issue appears to be related to the way metadata is included in the new alignments file format. The new meta and data fields are stored directly alongside frame data, so when an alignments file (in the new format) is loaded and checked for legacy landmarks, it attempts to read the face field for ...

O.k. ... Did as you suggested and it seemed to work....All the eyes closed shots actually had closed eyes....Then I re-added all the frames & faces with the closed eyes back into their respective extracted images folders & resumed training.......IT WENT BACKWARDS .... It seems to have litera...

While training I've noticed the program keeps trying to put the open eyes of the face I'm using over the closed eyes of the body I'm swapping it onto when the person blinks......Which is odd because both source face & source body are videos in which both subjects are blinking. It's like it can't...

I'm really new to this, but I'm wondering..... Since the program will already attempt to do a swap onto a person who's head has gone halfway out of shot.... For example, stood up quickly and you're getting a few seconds with only half a face....tip of a nose, mouth & chin... The program still do...