9ad9728b40
fix
2021-07-17 22:04:34 +04:00
336e0ca944
fix
2021-07-17 22:04:20 +04:00
8b71b83c94
fix
2021-07-17 22:03:59 +04:00
0748b8d043
AMP: removed eyes mouth prio option(default enabled), removed masked training option(default enabled).
2021-07-17 21:58:57 +04:00
959a3530f8
AMP: default morph factor is now 0.5. Preview shows with 1.0
2021-07-17 10:27:07 +04:00
da8f33ee85
removing fp16 for amp
2021-07-15 13:23:33 +04:00
c9e0ba1779
removing fp16 for sae
2021-07-15 13:22:32 +04:00
7b8991a3cc
fix help
2021-07-15 00:50:34 +04:00
f044c99ddc
remove ConvolutionAwareInitializer from layers, because lr-dropout does the same thing.
2021-07-15 00:50:11 +04:00
2edac3df8c
fix for clipgrad
2021-07-15 00:24:38 +04:00
35877dbfd7
AMP, SAEHD: added option use_fp16: Increases training/inference speed, reduces model size. Model may crash. Enable it after 1-5k iters.
...
AMP: removed lr_dropout, now it is enabled by default;
2021-07-14 23:03:54 +04:00
ee1bc83a14
AMP, SAEHD: reverted GAN to december version.
2021-07-07 21:45:43 +04:00
b4b72d056f
upd torrent link
2021-07-01 21:58:23 +04:00
9e0bd34253
update torrent link
2021-07-01 15:50:51 +04:00
446b95942f
fix
2021-07-01 15:08:11 +04:00
0444a9a565
default morph factor is now 0.1
2021-07-01 14:29:11 +04:00
075422e0c5
amp: fixes, removed pretrain option
2021-07-01 14:25:54 +04:00
63c794b3d0
rename dump_dflive to export_dfm
2021-06-28 18:26:54 +04:00
9d6b6feb1f
_
2021-06-28 14:27:09 +04:00
c43b3b161b
_
2021-06-27 20:43:44 +04:00
90a74efd89
fix
2021-06-26 23:06:30 +04:00
714234bce4
missing file
2021-06-26 18:03:04 +04:00
3c6bbe22b9
AMP: added Inter dimensions param. The model is not changed. Should be equal or more than AutoEncoder dimensions. More dims are better, but require more VRAM. You can fine-tune model size to fit your GPU.
2021-06-26 10:55:33 +04:00
5783191849
AMP: code refactoring, fix preview history
...
added dumpdflive command
2021-06-26 10:44:41 +04:00
6d89d7fa4c
_
2021-06-26 10:42:11 +04:00
9092e73c41
update QQ group
2021-06-18 17:15:08 +04:00
427e51b413
update QQ chinesse group
2021-06-18 17:13:29 +04:00
62f1d57871
AMP: fix a merge bug where morph_factor was always = 1.0
2021-06-14 17:58:01 +04:00
62c6fffdde
fix
2021-06-10 14:42:58 +04:00
9f0b4bf3cf
readme: added tiktok channel
2021-06-09 19:18:35 +04:00
6e0c8222f7
readme: added tiktok channel
2021-06-09 19:17:33 +04:00
5dc027a8b0
_
2021-06-09 19:17:18 +04:00
24ba84d4a5
MergeMasked: added full mask type as white square
2021-06-06 21:08:42 +04:00
2a95699b1c
upd windows magnet link
2021-06-03 00:00:40 +04:00
8ea7820b9c
fix
2021-06-03 00:00:28 +04:00
a6438ca494
upd magnet link
2021-06-01 13:30:06 +04:00
5fac5ee4f3
AMP model: added ‘morph_factor’ option. [0.1 .. 0.5]
...
The smaller the value, the more src-like facial expressions will appear.
The larger the value, the less space there is to train a large dst faceset in the neural network.
Typical fine value is 0.33
AMP model: added ‘pretrain’ mode as in SAEHD
Windows build: Default pretrain dataset is updated with applied Generic XSeg mask
2021-06-01 09:37:55 +04:00
34b62862e0
fix help msg
2021-06-01 09:36:53 +04:00
1981ed0ca8
_
2021-06-01 00:21:27 +04:00
315f241c51
upd magnet link
2021-05-30 14:28:23 +04:00
e52b53f87c
AMP fix
2021-05-30 09:24:23 +04:00
11a7993238
fix
2021-05-29 22:23:07 +04:00
6f86c68e65
add AMP model
2021-05-29 18:57:35 +04:00
e6e2ee7466
pixel_norm op
2021-05-25 14:26:48 +04:00
757283d10e
Trainer now saves every 25 min instead of 15
2021-05-25 14:23:25 +04:00
766750941a
Faceset packer now asks whether to delete the original files
2021-05-25 14:21:38 +04:00
41b517517e
XSegEditor , delete button now moves the face to _trash directory and it has been moved to the right border of the window
2021-05-25 14:17:34 +04:00
deedd3dd12
upd windows magnet link
2021-05-12 13:29:01 +04:00
66bb72f164
XSeg model has been changed to work better with large amount of various faces, thus you should retrain existing xseg model.
...
Windows build: Added Generic XSeg model pretrained on various faces. It is most suitable for src faceset because it contains clean faces, but also can be applied on dst footage without complex face obstructions.
2021-05-12 13:28:48 +04:00
65a703c024
SampleGeneratorFaceXSeg: additional sample augmentation for better generalization
2021-05-12 09:42:29 +04:00
iperov