d781af3d1f
removed TrueFace model. added SAEv2 model. Differences from SAE: + default e_ch_dims is now 21 + new encoder produces more stable face and less scale jitter before: https://i.imgur.com/4jUcol8.gifv after: https://i.imgur.com/lyiax49.gifv - scale of the face is less changed within frame size + decoder now has only 1 residual block instead of 2, result is same quality with less decoder size + added mid-full face, which covers 30% more area than half face. + added option " Enable 'true face' training " Enable it only after 50k iters, when the face is sharp enough. the result face will be more like src. The most src-like face with 'true-face-training' you can achieve with DF architecture.
#deepfakes #faceswap #face-swap #deep-learning #deeplearning #deep-neural-networks #deepface #deep-face-swap #fakeapp #fake-app #neural-networks #neural-nets
DeepFaceLab is a tool that utilizes machine learning to replace faces in videos.
If you like this software, please consider a donation.
GOAL: next DeepFacelab update.
bitcoin:31mPd6DxPCzbpCMZk4k1koWAbErSyqkAXr
-
Gallery
-
Manuals:
-
Prebuilt windows app
-
Forks
Google Colab fork by @chervonij
Linux fork by @lbfs - may be outdated
-
Ready to work facesets
-
Build and repository info
-
Communication groups:
(Chinese) QQ group 951138799 for ML/AI experts