github/DeepFaceLab
1
0
Fork 0
mirror of https://github.com/iperov/DeepFaceLab.git synced 2025-08-21 05:53:24 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

improvement SAE model. New option added. You should to restart training.

Browse source
This commit is contained in:
iperov 2019-01-12 10:10:50 +04:00
commit 46aa61050a
2 changed files with 78 additions and 57 deletions
Download patch file Download diff file Expand all files Collapse all files

4
README.md
View file

@ -70,7 +70,7 @@ LIAEF128 Cage video:
[![Watch the video](https://img.youtube.com/vi/mRsexePEVco/0.jpg)](https://www.youtube.com/watch?v=mRsexePEVco)
- **SAE (2GB+)** - Styled AutoEncoder. It is like LIAEF but with new face style loss. SAE more like face morpher/stylizer rather than direct swapper. Model has several options on start for fine tuning.
- **SAE (2GB+)** - Styled AutoEncoder - new superior model based on style loss. Morphing/stylizing done directly by neural network. Face obstructions also reconstructed without any masks. Converter mode 'overlay' should be used. Model has several options on start for fine tuning to fit your GPU.
![](https://github.com/iperov/DeepFaceLab/blob/master/doc/SAE_Cage_0.jpg)
@ -80,6 +80,8 @@ LIAEF128 Cage video:
SAE model Cage-Trump video: https://www.youtube.com/watch?v=2R_aqHBClUQ
SAE model Putin-Navalny video: https://www.youtube.com/watch?v=Jj7b3mqx-Mw
![](https://github.com/iperov/DeepFaceLab/blob/master/doc/DeepFaceLab_convertor_overview.png)