Pixel loss may help to enhance fine details and stabilize face color. Use it only if quality does not improve over time.
SAE:
previous SAE model will not work with this update.
Greatly decreased chance of model collapse.
Increased model accuracy.
Residual blocks now default and this option has been removed.
Improved 'learn mask'.
Added masked preview (switch by space key)
Converter:
fixed rct/lct in seamless mode
added mask mode (6) learned*FAN-prd*FAN-dst
added mask editor, its created for refining dataset for FANSeg model, and not for production, but you can spend your time and test it in regular fakes with face obstructions
- fixed nose missing one point
- made AA lines instead of regular ones
- made closed polylines for eyes and mouth
- reduced radius of circles for eyes, nose, and mouth as they obscure lines for small images
It could be difficult to tell if the point cloud was 'correct' or not
when manually fixing a face detection. For 68-point face landmarks, the
facial landmarks are now drawn to make it easier to tell if the face
is correctly detected.
