david/DeepFaceLab_Linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
1,079 Commits 1 Branch 0 Tags
3a3d121faeb02e82a209ca1afa918ba38e6c8189
Commit Graph
1079 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
david 3a3d121fae Add virtualenv manager and daemon runner script 2026-06-24 14:44:35 -04:00
david 5a732f1542 Add Flask-based Web UI and pipeline orchestrator 2026-06-24 14:36:18 -04:00
david dff277f3a9 Add DeepFaceLab submodule 2026-06-24 13:53:24 -04:00
david 7d23263fe9 Activate deepfacelab conda environment and add pretrain_Quick96 zip 2026-06-24 13:53:19 -04:00
Nicholas Georgescu 7187736a69 added gpu check and potential nvidia fix that works on some systems (#71) 2023-07-11 16:29:23 +03:00
Claudio Sánchez 8cda581d2c fix "no training data provided" (#69) 
* Update 6_train_Quick96.sh

Fix "no training data provided"

* Update 6_train_SAEHD.sh

fix "no training data provided"
 2023-01-24 13:27:17 +03:00
Maximilian Wolf 05482b3825 Create 6_export_SAEHD_as_dfm.sh and 6_export_AMP_as_dfm.sh (#68) 2022-11-23 23:38:55 +03:00
githubcatw 65ca4c8ba5 Add support for generic XSeg (#65) 
* Add generic XSeg
 2022-10-12 10:48:58 +03:00
Struchkov Mark 3f860b0be4 Update 3.1_denoise_data_dst_images.sh (#37) 2021-05-19 14:14:08 +03:00
Alex 797e9e026c While the conda does not have new CUDNN and cudatoolkit packages, we use packages for version 2.3. fix #24 
Thx for your attention, added the readme and changed the python version fix #25

HAPPY NEW YEAR!!!!!!!
 2020-12-31 15:18:00 +05:00
Alex 2d331d7f31 Update CUDNN and Cuda versions for TF 2.4 2020-12-26 14:32:50 +05:00
Deepak Mangla 6de7d2fa20 Fetch only latest revision of Repo. Full repo is too large. (#15) 2020-12-09 12:48:22 +05:00
Alex 85ea2aeae7 Update README.md 
Fix #20
 2020-12-09 12:45:25 +05:00
Alex 497c5625b0 Update README.md 
upd cudatoolkit version
 2020-12-03 22:32:21 +05:00
Alex 1e462d454e update README.md 
Add new scripts download pretrains.

fix path in env.sh
 2020-09-19 03:20:21 +03:00
Alex 86e7ec7df1 Update README.md 2020-08-31 10:37:09 +03:00
Dogan Kurt 18f695af20 Update 5_XSeg_data_src_mask_apply.sh (#2) 2020-08-18 11:00:59 +03:00
Dogan Kurt d53b07b7ac Update 5_XSeg_data_dst_mask_apply.sh (#1) 2020-08-18 10:58:53 +03:00
Alex 0e6f7891ba Merge pull request #3 from dodobyte/patch-3 
Update README.md
 2020-08-18 12:56:00 +05:00
Alex ce5aa6cb73 Merge pull request #4 from dodobyte/patch-4 
Create 5_XSeg_data_src_mask_edit.sh
 2020-08-18 12:40:16 +05:00
Dogan Kurt 2b78bf2cbf Create 5_XSeg_data_src_mask_edit.sh 2020-08-07 16:33:53 +02:00
Dogan Kurt 3ea31a9822 Update README.md 2020-08-07 16:31:00 +02:00
Alex b08a57a594 add README.md 2020-08-05 00:34:00 +03:00
Alex 4bee8f184e add all scripts from original DFL 2020-08-05 00:31:25 +03:00
Alex 71ceb60719 Forked from iperov/DeepFaceLab 2020-08-04 01:04:26 +03:00
Colombo 3e7ee22ae3 Merger: fix load time of xseg if it has no model files 2020-07-29 00:41:53 +04:00
Colombo 6134e57762 options_show_override{} for model summary in pretrain mode 2020-07-27 16:37:13 +04:00
Colombo 1435dd3dd1 SAEHD: now random_warp is disabled for pretraining mode by default 2020-07-26 16:11:08 +04:00
Colombo ce95af9068 SAEHD: write_preview_history now works faster 
The frequency at which the preview is saved now depends on the resolution.
For example 64x64 – every 10 iters. 448x448 – every 70 iters.
 2020-07-18 11:03:13 +04:00
Colombo 58670722dc fix 2020-07-17 17:40:32 +04:00
Colombo b9b97861e1 fix mask for style losses 2020-07-17 17:34:07 +04:00
Colombo 0efebe6bc5 upd deepfake_progress.png 2020-07-17 15:56:35 +04:00
Colombo 3930073e32 Merger: added option “Number of workers?” 
Specify the number of threads to process.
A low value may affect performance.
A high value may result in memory error.
The value may not be greater than CPU cores.
 2020-07-17 15:46:01 +04:00
Colombo dd21880ecd fix 2020-07-16 23:39:56 +04:00
Colombo 6c7bb74ad4 README: update deepfake_progress, 448 pix 2020-07-16 22:26:43 +04:00
Colombo e8b04053e4 SAEHD: 
Changed help for “Learning rate dropout” option:

When the face is trained enough, you can enable this option to get extra sharpness and reduce subpixel shake for less amount of iterations.

Enabled it before “disable random warp” and before GAN. n disabled. y enabled

cpu enabled on CPU. This allows not to use extra VRAM, sacrificing 20% time of iteration.

 Changed help for GAN option:

Train the network in Generative Adversarial manner.

Forces the neural network to learn small details of the face.

Enable it only when the face is trained enough and don't disable.

Typical value is 0.1

improved GAN. Now it produces better skin detail, less patterned aggressive artifacts, works faster.
https://i.imgur.com/Nbh3mw1.png
 2020-07-16 22:19:17 +04:00
Colombo aacd29269a fix 2020-07-16 22:11:23 +04:00
Colombo c963703395 fix 2020-07-08 18:16:29 +04:00
Colombo 5a40f537cc . 2020-07-04 07:58:53 +04:00
Colombo 9a540e644c upd leras ops 2020-07-03 19:32:14 +04:00
Colombo 11dc7d41a0 upd SampleProcessor 2020-07-03 19:31:21 +04:00
Colombo b0ad36de94 upd cv2ex 2020-07-03 19:30:52 +04:00
Colombo 3283dce96a interact: change to waitKeyEx 2020-07-03 18:43:18 +04:00
Colombo c58d2e8fb3 fix cv2.resize interpolation 2020-07-03 18:41:42 +04:00
Colombo 770da74a9b fix cv2.resize interpolation 2020-07-03 18:40:35 +04:00
Colombo 55c51578e5 fix bicubic interpolation in xsegeditor 2020-07-03 18:38:53 +04:00
Colombo 57ea3e61b7 fix extractor 2020-07-03 16:06:06 +04:00
Colombo 4ce4997d1a fix 2020-07-03 15:19:12 +04:00
Colombo 81ed7c0a2a fix 2020-07-03 15:18:15 +04:00
Colombo f56df85f78 fix manual extractor 2020-07-03 15:07:42 +04:00