CalvinBackup/iperov-DeepFaceLab
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update readme

Browse Source
This commit is contained in:
iperov
2018-07-01 11:53:55 +04:00
parent 46b2aa86da
commit f9fb1351fb
1 changed files with 7 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+7 -3
View File
@@ -102,6 +102,12 @@ dst - controller face (your face)
converter --input-dir must contains *extracted dst faces* in sequence to be converted, its mean you can train on 1500 dst faces, but use only 100 for convert. converter --input-dir must contains *extracted dst faces* in sequence to be converted, its mean you can train on 1500 dst faces, but use only 100 for convert.
- Video comparison of different Cage facesets.
Vertical: 1 - mix of various Cage face shape and light conditions. 2,3,4 - without mix.
Horizontal: 1 - DF, 2 - LIAEF128.
[![](https://img.youtube.com/vi/C1nFgrmtm_o/0.jpg)](https://youtu.be/C1nFgrmtm_o)
Conclusion: **better not to mix and use only same shape faces with same light**
### **Sort tool**: ### **Sort tool**:
`hist` groups images by similar content `hist` groups images by similar content
@@ -132,9 +138,7 @@ Best practice for dst faces:
### **Facesets**: ### **Facesets**:
- Nicolas Cage. - Nicolas Cage 4 facesets (1 mix + 3 different)
- Cage/Trump workspace
download from here: https://mega.nz/#F!y1ERHDaL!PPwg01PQZk0FhWLVo5_MaQ download from here: https://mega.nz/#F!y1ERHDaL!PPwg01PQZk0FhWLVo5_MaQ