[MrDeepfakes pretraining written by SPT from 01/06/2023]
This works only for pretraining !
It's made of celebs from CelebA pack, removed all men, removed 2000-3000 shittiest quality pictures, added 3000-4000 NEW porn faces extracted from hq porn photosets.
Usage :
Download, put it in DeepFaceLab_NVIDIA\_internal\pretrain_CelebA (save the original pak if needed)
Choose a new model, any archi and resolution you want, don't use any options besides Pre-train, and random warp until 50k-100k training, then disable RW. Train up to 175-200k (can go up to 400k or more if you feel like it, but it's usable from 175k).
Note : some people think Pre-train models should always use Random Warp, maybe they're right, please comment about this, I'm not sure. I just stop RW when loss values stop progressing at a satisfying pace.
Save this model somewhere, use a copy of it to start training a new deepfake, by disabling Pretrain parameter. It will start from 0 but will go up to a satisfying level faster (with 175k pretraining, 60k was enough training for the 1st deepfake I did with it). Re-use copy of base pretrained model for each new celeb you'll fake.
Images in the faceset are 512x512 resolution.
Download :
https://mega.nz/file/858WiQoZ#xhisXQsZV6vFzSLP0-nlQnRSbAylsFVqmxShKmJdVyk
Last edited:
