1
0
Fork 0
mirror of https://github.com/deepfakes/faceswap synced 2025-06-09 04:36:50 -04:00
Commit graph

59 commits

Author SHA1 Message Date
Gareth Dunstone
2633da9ed7
frame-range changes (#92)
* extended arguments for convert re https://github.com/deepfakes/faceswap/issues/85

* forgot to change helptext for extended arguments.

* Added -fr --frame-range argument to convert

accepts a list of frame ranges like `-fr 40-50 90-100`

still writes out frames that havent been converted.

* added --discard-frames argument

--discard-frames discards frames not included in --frame-range instead
of writing them out unchanged.

* Made training message slightly clearer

* Revert "Made training message slightly clearer"

This reverts commit 25a9744aea.

* Training status now '\r's rather than newlines.
Maybe its good, maybe its bad.
I like it.

* fixing https://github.com/deepfakes/faceswap/pull/90#issuecomment-362309166
2018-02-02 03:11:26 +11:00
Gareth Dunstone
0f8d9db826
frame-range option for convert (#90)
* extended arguments for convert re https://github.com/deepfakes/faceswap/issues/85

* forgot to change helptext for extended arguments.

* Added -fr --frame-range argument to convert

accepts a list of frame ranges like `-fr 40-50 90-100`

still writes out frames that havent been converted.

* added --discard-frames argument

--discard-frames discards frames not included in --frame-range instead
of writing them out unchanged.
2018-02-02 00:46:42 +11:00
Gareth Dunstone
7e7cf0bd2d
extended arguments for convert.py (#89)
* extended arguments for convert re https://github.com/deepfakes/faceswap/issues/85

* helptext for extended arguments.

* changed default mask type to facehullandrect
2018-02-01 23:19:03 +11:00
Clorr
34945cfcd7
Adding models as plugins + Face filtering (#53) + #39 + #43 + #44 + #49 (#61)
* Making Models as plugins

* Do not reload model on each image #39 + Adding FaceFilter #53

* Adding @lukaville PR for #43 and #44 (possibly)

* Training done in a separate thread

* Better log for plugin load

* Adding a prefetch to train.py #49
(Note that we prefetch 2 batches of images, due to the queue behavior)
+ More compact logging with verbose info included

* correction of DirectoryProcessor signature

* adding missing import

* Convert with parallel preprocessing of files

* Added coverage var for trainer

Added a var with comment. Feel free to add it as argument

* corrections

* Modifying preview and normalization of image + correction

* Cleanup
2018-01-31 18:56:44 +01:00
Clorr
e518206c8e Adding PluginLoader 2018-01-03 14:01:02 +01:00
Clorr
bb489f4f51 Adding new plugins (Extract_Align & Convert_Masked) 2018-01-03 10:33:42 +01:00
Clorr
3e2976ab03 Adding plugins 2018-01-03 10:33:39 +01:00
Hidde Jansen
d493cadeca
Allow users to swap the A/B models (#29)
* Allow users to swap the conversion models.
2017-12-27 12:47:52 +01:00
Édouard WILLISSECK
59d234ae5e Unified CLI (#22)
* Created a single script to call the other ones.

Usage is ./faceswap.py {train|extract|convert}

* Improved the help from the commands.

* Added forgotten faceswap.py file.

* Changed gitignore to add the scripts.

* Updates gitignore.

* Added guarding not to execute code when imported.

* Removed useless script. Display help when no arguments are provided.

* Update README
2017-12-25 02:17:02 +01:00
Renamed from convert.py (Browse further)