Basic usage instruction: https://i.imgur.com/w7LkId2.jpg
'whole_face' requires skill in Adobe After Effects.
For using whole_face you have to extract whole_face's by using
4) data_src extract whole_face
and
5) data_dst extract whole_face
Images will be extracted in 512 resolution, so they can be used for regular full_face's and half_face's.
'whole_face' covers whole area of face include forehead in training square,
but training mask is still 'full_face'
therefore it requires manual final masking and composing in Adobe After Effects.
added option 'masked_training'
This option is available only for 'whole_face' type.
Default is ON.
Masked training clips training area to full_face mask,
thus network will train the faces properly.
When the face is trained enough, disable this option to train all area of the frame.
Merge with 'raw-rgb' mode, then use Adobe After Effects to manually mask, tune color, and compose whole face include forehead.
added option Eyes priority (y/n)
fix eye problems during training ( especially on HD architectures )
by forcing the neural network to train eyes with higher priority
before/after https://i.imgur.com/YQHOuSR.jpg
It does not guarantee the right eye direction.
added smooth_rect option
default is ON.
Decreases jitter of predicting rect by using temporal interpolation.
You can disable this option if you have problems with dynamic scenes.
Removed the wait at first launch for most graphics cards.
Increased speed of training by 10-20%, but you have to retrain all models from scratch.
SAEHD:
added option 'use float16'
Experimental option. Reduces the model size by half.
Increases the speed of training.
Decreases the accuracy of the model.
The model may collapse or not train.
Model may not learn the mask in large resolutions.
true_face_training option is replaced by
"True face power". 0.0000 .. 1.0
Experimental option. Discriminates the result face to be more like the src face. Higher value - stronger discrimination.
Comparison - https://i.imgur.com/czScS9q.png
More stable and precise version of the face transformation matrix.
Now full_faces are aligned with the upper and lateral boundaries of the frame,
result: fix of cutted mouth, increase area of the cheeks of side faces
before/after https://i.imgur.com/t9IyGZv.jpg
therefore, additional training is required for existing models.
Optionally, you can re-extract dst faces of your project, if they have problems with cutted mouth or cheeks.
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.
fixed model sizes from previous update.
avoided bug in ML framework(keras) that forces to train the model on random noise.
Converter: added blur on the same keys as sharpness
Added new model 'TrueFace'. This is a GAN model ported from https://github.com/NVlabs/FUNIT
Model produces near zero morphing and high detail face.
Model has higher failure rate than other models.
Keep src and dst faceset in same lighting conditions.
Session is now saved to the model folder.
blur and erode ranges are increased to -400+400
hist-match-bw is now replaced with seamless2 mode.
Added 'ebs' color transfer mode (works only on Windows).
FANSEG model (used in FAN-x mask modes) is retrained with new model configuration
and now produces better precision and less jitter
With interactive converter you can change any parameter of any frame and see the result in real time.
Converter: added motion_blur_power param.
Motion blur is applied by precomputed motion vectors.
So the moving face will look more realistic.
RecycleGAN model is removed.
Added experimental AVATAR model. Minimum required VRAM is 6GB (NVIDIA), 12GB (AMD)
Usage:
1) place data_src.mp4 10-20min square resolution video of news reporter sitting at the table with static background,
other faces should not appear in frames.
2) process "extract images from video data_src.bat" with FULL fps
3) place data_dst.mp4 video of face who will control the src face
4) process "extract images from video data_dst FULL FPS.bat"
5) process "data_src mark faces S3FD best GPU.bat"
6) process "data_dst extract unaligned faces S3FD best GPU.bat"
7) train AVATAR.bat stage 1, tune batch size to maximum for your card (32 for 6GB), train to 50k+ iters.
8) train AVATAR.bat stage 2, tune batch size to maximum for your card (4 for 6GB), train to decent sharpness.
9) convert AVATAR.bat
10) converted to mp4.bat
updated versions of modules
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.
