Maximum resolution is increased to 640.
‘hd’ archi is removed. ‘hd’ was experimental archi created to remove subpixel shake, but ‘lr_dropout’ and ‘disable random warping’ do that better.
‘uhd’ is renamed to ‘-u’
dfuhd and liaeuhd will be automatically renamed to df-u and liae-u in existing models.
Added new experimental archi (key -d) which doubles the resolution using the same computation cost.
It is mean same configs will be x2 faster, or for example you can set 448 resolution and it will train as 224.
Strongly recommended not to train from scratch and use pretrained models.
New archi naming:
'df' keeps more identity-preserved face.
'liae' can fix overly different face shapes.
'-u' increased likeness of the face.
'-d' (experimental) doubling the resolution using the same computation cost
Examples: df, liae, df-d, df-ud, liae-ud, ...
Improved GAN training (GAN_power option). It was used for dst model, but actually we don’t need it for dst.
Instead, a second src GAN model with x2 smaller patch size was added, so the overall quality for hi-res models should be higher.
Added option ‘Uniform yaw distribution of samples (y/n)’:
Helps to fix blurry side faces due to small amount of them in the faceset.
Quick96:
Now based on df-ud archi and 20% faster.
XSeg trainer:
Improved sample generator.
Now it randomly adds the background from other samples.
Result is reduced chance of random mask noise on the area outside the face.
Now you can specify ‘batch_size’ in range 2-16.
Reduced size of samples with applied XSeg mask. Thus size of packed samples with applied xseg mask is also reduced.
‘cpu’ mean enabled on CPU. This allows not to use extra VRAM, sacrificing 20% time of iteration.
SAEHD: resolution >= 256 now has second dssim loss function
Now you can replace the head.
Example: https://www.youtube.com/watch?v=xr5FHd0AdlQ
Requirements:
Post processing skill in Adobe After Effects or Davinci Resolve.
Usage:
1) Find suitable dst footage with the monotonous background behind head
2) Use “extract head” script
3) Gather rich src headset from only one scene (same color and haircut)
4) Mask whole head for src and dst using XSeg editor
5) Train XSeg
6) Apply trained XSeg mask for src and dst headsets
7) Train SAEHD using ‘head’ face_type as regular deepfake model with DF archi. You can use pretrained model for head. Minimum recommended resolution for head is 224.
8) Extract multiple tracks, using Merger:
a. Raw-rgb
b. XSeg-prd mask
c. XSeg-dst mask
9) Using AAE or DavinciResolve, do:
a. Hide source head using XSeg-prd mask: content-aware-fill, clone-stamp, background retraction, or other technique
b. Overlay new head using XSeg-dst mask
Warning: Head faceset can be used for whole_face or less types of training only with XSeg masking.
XSegEditor: added button ‘view trained XSeg mask’, so you can see which frames should be masked to improve mask quality.
New help messages for these options:
Face style power
Learn the color of the predicted face to be the same as dst inside mask.
If you want to use this option with 'whole_face' you have to use XSeg trained mask.
Warning: Enable it only after 10k iters, when predicted face is clear enough to start learn style.
Start from 0.001 value and check history changes.
Enabling this option increases the chance of model collapse
Background style power
Learn the area outside mask of the predicted face to be the same as dst.
If you want to use this option with 'whole_face' you have to use XSeg trained mask.
This can make face more like dst.
Enabling this option increases the chance of model collapse. Typical value is 2.0
for every batch_size*16 samples,
model collects the samples with the highest error and learns them again
therefore hard samples will be trained more often
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.
SAEHD:
added new option
GAN power 0.0 .. 10.0
Train the network in Generative Adversarial manner.
Forces the neural network to learn small details of the face.
You can enable/disable this option at any time,
but better to enable it when the network is trained enough.
Typical value is 1.0
GAN power with pretrain mode will not work.
Example of enabling GAN on 81k iters +5k iters
https://i.imgur.com/OdXHLhU.jpghttps://i.imgur.com/CYAJmJx.jpg
dfhd: default Decoder dimensions are now 48
the preview for 256 res is now correctly displayed
fixed model naming/renaming/removing
Improvements for those involved in post-processing in AfterEffects:
Codec is reverted back to x264 in order to properly use in AfterEffects and video players.
Merger now always outputs the mask to workspace\data_dst\merged_mask
removed raw modes except raw-rgb
raw-rgb mode now outputs selected face mask_mode (before square mask)
'export alpha mask' button is replaced by 'show alpha mask'.
You can view the alpha mask without recompute the frames.
8) 'merged *.bat' now also output 'result_mask.' video file.
8) 'merged lossless' now uses x264 lossless codec (before PNG codec)
result_mask video file is always lossless.
Thus you can use result_mask video file as mask layer in the AfterEffects.
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
If you want, you can manually remove unnecessary angles from src faceset after sort by yaw.
Optimized sample generators (CPU workers). Now they consume less amount of RAM and work faster.
added
4.2.other) data_src/dst util faceset pack.bat
Packs /aligned/ samples into one /aligned/samples.pak file.
After that, all faces will be deleted.
4.2.other) data_src/dst util faceset unpack.bat
unpacks faces from /aligned/samples.pak to /aligned/ dir.
After that, samples.pak will be deleted.
Packed faceset load and work faster.
