Faceswap Forum

Hey Bryan, thanks a lot for the detailed and informative answer. I am lucky to be able to get the correct kind of data to train on, in my last set we captured 8k res images. Around 100k images per subject to train on. However I understand now that it is the architecture that is also a limiter. Topaz...

Hi Friends, I have been successfully training deepfake models for a good few months now, and I am taking some time to research and plan the next iteration of my process. I was reading that the Apple M processors have unified memory, which would be a god send for large resolution and batch training. ...