DeepFaceLab is a tool that utilizes deep learning to recognize and swap faces in pictures and videos.
-
new models
-
new architecture, easy to experiment with models
-
works on 2GB old cards , such as GT730. Example of fake trained on 2GB gtx850m notebook in 18 hours https://www.youtube.com/watch?v=bprVuRxBA34
-
face data embedded to png files
-
automatic GPU manager, chooses best gpu(s) and supports --multi-gpu (only for identical cards). Warning: dont use cards in SLI mode.
-
cpu mode. 8th gen Intel core CPU able to train H64 model in 2 days.
-
new preview window
-
extractor in parallel
-
converter in parallel
-
added --debug option for all stages
-
added MTCNN extractor which produce less jittered aligned face than DLIBCNN, but can produce more false faces. Comparison dlib (at left) vs mtcnn on hard case:
MTCNN produces less jitter.
-
added Manual extractor. You can fix missed faces manually or do full manual extract:
-
standalone zero dependencies ready to work prebuilt binary for all windows versions, see below
Warning: Facesets of FaceSwap or FakeApp are not compatible with this repo. You should to run extract again.
- H64 (2GB+) - half face with 64 resolution. It is as original FakeApp or FaceSwap, but with new TensorFlow 1.8 DSSIM Loss func and separated mask decoder + better ConverterMasked. for 2GB and 3GB VRAM model works in reduced mode.
H64 Robert Downey Jr.:
- H128 (3GB+) - as H64, but in 128 resolution. Better face details. for 3GB and 4GB VRAM model works in reduced mode.
H128 Cage:
H128 asian face on blurry target:
- DF (5GB+) - @dfaker model. As H128, but fullface model. Strongly recommended not to mix various light conditions in src faces.
- LIAEF128 (5GB+) - Less agressive Improved Autoencoder Fullface 128 model. Result of combining DF, IAE, + experiments. Model tries to morph src face to dst, while keeping facial features of src face, but less agressive morphing. Model has problems with closed eyes recognizing.
LIAEF128 Cage:
LIAEF128 Cage video:
- UFM (4GB+) - U-net Face Morpher model. If "match_style" option choosed, then this model tries to morph src face to target face and fill around face same background. UFM is result of combining modified U-Net, classic face autoencoder, DSSIM and style losses.
blur
places most blurred faces at end of folder
hist
groups images by similar content
hist-dissim
places most similar to each other images to end.
hist-blur
sort by blur in groups of similar content
brightness
hue
black
Places images which contains black area at end of folder. Useful to get rid of src faces which cutted by screen.
Best practice for gather src faceset:
- delete first unsorted aligned groups of images what you can to delete. Dont touch target face mixed with others.
black
-> delete faces cutted by black area at end of folderblur
-> delete 30-50% at end of folderhist
-> delete groups of similar and leave only target facehist-dissim
-> leave only first 1500 facesface-yaw
-> just for finalize faceset
Best practice for dst faces:
- delete first unsorted aligned groups of images what you can to delete. Dont touch target face mixed with others.
hist
-> delete groups of similar and leave only target face
-
Nicolas Cage 4 facesets (1 mix + 3 different)
-
Steve Jobs
download from here: https://mega.nz/#F!y1ERHDaL!PPwg01PQZk0FhWLVo5_MaQ
dlib==19.10.0 from pip compiled without CUDA. Therefore you have to compile DLIB manually.
Command line example for windows: python setup.py install -G "Visual Studio 14 2015" --yes DLIB_USE_CUDA
CPU mode enabled by arg --cpu-only for all stages. Follow requirements-cpu.txt to install req packages. Do not use DLIB extractor in CPU mode, its too slow. Only H64 model reasonable to train on home CPU.
This repo supports only windows build of scripts. If you want to support mac/linux/docker - create such fork, it will be referenced here.
Windows 7,8,8.1,10 zero dependency (just install/update your GeForce Drivers) prebuilt DeepFaceLab (include GPU and CPU versions) can be downloaded from
- torrent https://rutracker.org/forum/viewtopic.php?p=75318742 (magnet link inside).
- https://mega.nz/#F!b9MzCK4B!zEAG9txu7uaRUjXz9PtBqg
Video tutorial: https://www.youtube.com/watch?v=K98nTNjXkq8
Windows 10 consumes % of VRAM even if card unused for video output.
algorithm of overlaying neural face onto video face located in ConverterMasked.py. Can someone implement adaptive histogram matching to prevent glares when a dark eyes face merges onto a light eyes face ?