mirror of
https://github.com/iperov/DeepFaceLab.git
synced 2025-08-20 13:33:24 -07:00
upd readme
This commit is contained in:
parent
d8833e929e
commit
e069b839f1
9 changed files with 220 additions and 209 deletions
27
doc/doc_features.md
Normal file
27
doc/doc_features.md
Normal file
|
@ -0,0 +1,27 @@
|
|||
### **Features**:
|
||||
|
||||
- standalone zero dependencies ready to work prebuilt binary for all windows versions, see below
|
||||
|
||||
- new models
|
||||
|
||||
- new architecture, easy to experiment with models
|
||||
|
||||
- face data embedded to JPG files
|
||||
|
||||
- cpu mode. 8th gen Intel core CPU able to train H64 model in 2 days.
|
||||
|
||||
- new preview window
|
||||
|
||||
- extractor in parallel
|
||||
|
||||
- converter in parallel
|
||||
|
||||
- **--debug** option for all stages
|
||||
|
||||
- **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.
|
||||
|
||||
- **Manual extractor**. You can fix missed faces manually or do full manual extract:
|
||||

|
||||

|
Loading…
Add table
Add a link
Reference in a new issue