Commit Graph

Select branches

Hide Pull Requests

AMP

DFL-1.0

master

#10

#11

#117

#147

#152

#153

#156

#157

#159

#16

#169

#184

#189

#19

#190

#20

#203

#206

#221

#239

#242

#245

#261

#267

#283

#291

#314

#316

#322

#331

#340

#348

#349

#353

#356

#360

#383

#387

#391

#393

#410

#417

#425

#442

#448

#45

#454

#457

#46

#461

#47

#485

#501

#5211

#5231

#5238

#524

#525

#5264

#5264

#5286

#5291

#5295

#5299

#5301

#5314

#5334

#5350

#5364

#537

#5370

#5371

#5372

#5373

#5378

#5388

#5413

#5425

#5437

#5441

#5460

#5500

#5505

#5522

#5523

#5545

#5563

#5567

#5568

#5593

#5618

#5621

#5627

#5638

#5638

#5662

#5662

#5665

#5665

#5676

#5680

#5680

#5689

#5689

#5690

#5690

#5718

#5722

#573

#5733

#5733

#5742

#580

#585

#590

#597

#670

#671

#672

#699

#716

#717

#718

#734

#750

#767

#769

#774

#776

#783

#794

#8

#822

#885

#91

#926

#94

#948

#95

DF.wf.288res.384.92.72.22

pretrained

Mono Color

• 75eeef0a96 fix for amd Colombo 2019-10-24 21:59:13 +04:00
• 0448a461f5 fix umeyama for landmark alignment of side faces Before https://i.imgur.com/pEoZ6Mu.mp4 after https://i.imgur.com/wO2Guo7.mp4 Colombo 2019-10-24 21:46:54 +04:00
• 59d6fada23 draw up arrow in the red landmark debug square Colombo 2019-10-24 10:09:51 +04:00
• 734d97d729 added 'sort by vggface': sorting by face similarity using VGGFace model. Requires 4GB+ VRAM and internet connection for the first run. Colombo 2019-10-23 15:06:39 +04:00
• 0d3b25812d fix Colombo 2019-10-20 18:02:23 +04:00
• d3e35c8ce6 enhanced sort by final: now faces are evenly distributed not only in the direction of yaw, but also in pitch Colombo 2019-10-20 14:18:14 +04:00
• e63e89c305 fix s3fd extractor bug for 11GB+ cards Colombo 2019-10-17 22:25:23 +04:00
• e3f63a7b40 fix Colombo 2019-10-15 17:37:16 +04:00
• 73511a072a SAE/SAEHD: removed option 'apply random ct' Colombo 2019-10-15 11:22:19 +04:00
• 5a2eefaa5b removed last fix Colombo 2019-10-14 20:31:11 +04:00
• e18b07549b new fix of "fixed bug when the same face could be detected twice" Colombo 2019-10-14 20:26:53 +04:00
• 85cbdcd290 revert fix "face could be detected twice" Colombo 2019-10-14 19:11:49 +04:00
• 5ad4b1011c refactoring after @kcimit Colombo 2019-10-14 17:20:43 +04:00
• d26ac4896e Restore mask functionality in mask editor (#442) kcimit 2019-10-14 15:14:57 +02:00
• 24eac44dd9 fix random_flip option bug Colombo 2019-10-14 14:08:36 +04:00
• 1de1e0029f Extractor now produces a less shaked face. but second pass is now slower by 25%, before/after: https://imgur.com/L77puLH Colombo 2019-10-14 12:09:32 +04:00
• e013cb0f6b moving some files Colombo 2019-10-14 09:34:44 +04:00
• 2b264da86b fixed bug when same face can be detected twice Colombo 2019-10-13 14:59:50 +04:00
• aa523b3f2e change name Colombo 2019-10-12 16:13:23 +04:00
• 91d2391ac9 fix Colombo 2019-10-12 14:09:48 +04:00
• 8595c757ad change options order Colombo 2019-10-12 10:39:48 +04:00
• 92f14dee70 SAEHD: added option Enable random warp of samples, default is on Random warp is required to generalize facial expressions of both faces. When the face is trained enough, you can disable it to get extra sharpness for less amount of iterations. Colombo 2019-10-12 10:31:50 +04:00
• e15f846d08 SAE, SAEHD: random flip and learn mask options now can be overridden Colombo 2019-10-10 22:56:57 +04:00
• 1f27d13f61 clip border for midface Colombo 2019-10-10 14:48:51 +04:00
• 63ecd4ec34 speed up S3FD extraction for GPU with >= 11GB vram Colombo 2019-10-10 13:22:14 +04:00
• 59ad734b6c fixed GPU indexing Colombo 2019-10-10 13:13:36 +04:00
• d2d0dcb5e7 fix multigpu extractor Colombo 2019-10-10 13:01:57 +04:00
• 9b08199e87 upd .md Colombo 2019-10-09 12:01:37 +04:00
• 3f23135982 SAEHD: speed up for nvidia, duplicate code clean up Colombo 2019-10-08 21:02:20 +04:00
• 627df082d7 fix for plaidml Colombo 2019-10-08 16:55:21 +04:00
• ac7725163d removed SAEv2, Colombo 2019-10-08 15:09:28 +04:00
• cbc18b2d41 nothing interesting Colombo 2019-10-06 17:55:32 +04:00
• 4c2cb44643 upd liae loss Colombo 2019-10-06 10:06:22 +04:00
• e4a360e5ff upd loss Colombo 2019-10-06 01:00:34 +04:00
• d781af3d1f fixed GPU detection and indexes, got rid of using nvml, now using direct cuda lib to determine gpu info that match tensorflow indexes, Colombo 2019-10-05 16:26:23 +04:00
• 353bcdf80f cuda_cache_max_size Colombo 2019-10-02 20:17:56 +04:00
• 09a990852f funits models: cleaning code Colombo 2019-09-27 18:48:01 +04:00
• 8041ee959a nnlib initialization: fix choosing best gpu when indexes of gpu are different in tf and nvsmi Colombo 2019-09-27 18:47:18 +04:00
• 4a2203cc35 adding kernel initializer option to FUNITAdain block Colombo 2019-09-24 21:30:28 +04:00
• deeb98474b fix funit Colombo 2019-09-23 18:54:37 +04:00
• 9e80bbc917 1 Colombo 2019-09-21 15:19:58 +04:00
• 62682351ac fix avatar model Colombo 2019-09-21 14:48:40 +04:00
• 2a3b3f0021 added tf_cpu_mode option for funit models Colombo 2019-09-21 09:44:34 +04:00
• d9d10f91c2 S3FD and 2DFAN-4 were improperly ported from pytorch. now fixed. Colombo 2019-09-20 17:16:37 +04:00
• e928ee0d30 1 Colombo 2019-09-19 19:36:46 +04:00
• ef90316f27 1 Colombo 2019-09-19 17:29:12 +04:00
• a325d0353b fix Colombo 2019-09-19 11:20:30 +04:00
• c06d073936 1 Colombo 2019-09-19 11:16:35 +04:00
• dc11ec32be SAE : WARNING, RETRAIN IS REQUIRED ! fixed model sizes from previous update. avoided bug in ML framework(keras) that forces to train the model on random noise. Colombo 2019-09-19 11:13:56 +04:00
• 201b762541 SAE: fix Colombo 2019-09-14 16:39:47 +04:00
• b6b92bded0 converter: now writes a filename of current frame config, SAE: removed multiscale decoder, because it's not effective Colombo 2019-09-13 08:59:00 +04:00
• bef4e5d33c Converter: added new color transfer modes: mkl, mkl-m, idt, idt-m Colombo 2019-09-07 22:01:01 +04:00
• 7ed38a8097 Converter: Colombo 2019-09-07 13:57:42 +04:00
• 70dada42ea fix Colombo 2019-09-06 14:52:46 +04:00
• faa14c4e59 fix extractor error on load grayscale images Colombo 2019-09-06 11:54:49 +04:00
• bc0b25cdda interactive converter now saves the session. if input frames are changed (amount or filenames) then interactive converter automatically starts a new session. if model is more trained then all frames will be recomputed again with their saved configs. Colombo 2019-08-30 16:19:41 +04:00
• bac9d5a99d nothing interesting Colombo 2019-08-30 09:49:07 +04:00
• 9f58d160a0 Converter: fix output names of merged files, now its 100% same as input, ConvertAvatar: fix input image after fix landmarks face align, VideoEd: video_from_sequence now uses pipe input to input any filenames instead of %.5d. formatted Colombo 2019-08-27 22:05:22 +04:00
• 23854ac8bc removing landmarks of lips which are used in face aligning, and leave only corners of mouth landmarks, result: less scale jittering aligning that will be feeded into AE and produce more stable face before: https://i.imgur.com/gJaW5Y4.gifv after: https://i.imgur.com/Vq7gvhY.gifv iperov 2019-08-26 19:36:41 +04:00
• fb4837b3cb fix converter iperov 2019-08-26 11:03:57 +04:00
• 78ddd51ffc fix interactive converter iperov 2019-08-26 10:47:20 +04:00
• 96d0e3fbee converter output filename - fixed indexing, now starts from 00001 as extracted frames iperov 2019-08-26 10:39:04 +04:00
• 029cabea3d minor fix iperov 2019-08-26 10:03:10 +04:00
• d3eadbf5f3 upd readme iperov 2019-08-26 09:51:32 +04:00
• 6243190f74 fix help screen iperov 2019-08-26 08:14:31 +04:00
• 25da22fdc9 minor fix iperov 2019-08-25 22:32:21 +04:00
• 63d30c49ae fixes and optimizations, converters: added new option sharpen_mode and sharpen_amount iperov 2019-08-25 19:18:51 +04:00
• c39ed9d9c9 updated pdf manuals for AVATAR model. Avatar converter: added super resolution option. All converters: super resolution DCSCN network is now replaced by RankSRGAN iperov 2019-08-25 17:43:52 +04:00
• 19c66286da fix gen_warp_params now accepts any square images iperov 2019-08-25 14:06:33 +04:00
• 6c66495bcf default avatar type option is now HEAD. Head produces stable result. iperov 2019-08-25 08:16:54 +04:00
• d129b5dd7f sort data for CAInitializerMP iperov 2019-08-25 07:50:27 +04:00
• 00dce38187 fix iperov 2019-08-25 07:43:22 +04:00
• b572b8f4d4 fix ConverterConfig iperov 2019-08-25 00:30:05 +04:00
• e3505d9b8c fix AVATARModel iperov 2019-08-24 20:33:29 +04:00
• 5968ac21f6 fix AVATARModel iperov 2019-08-24 19:55:38 +04:00
• 2a9a579436 fix iperov 2019-08-24 13:23:15 +04:00
• 407ce3b1ca Added interactive converter. With interactive converter you can change any parameter of any frame and see the result in real time. iperov 2019-08-24 12:57:29 +04:00
• 3f0bf2e994 upd readme iperov 2019-08-20 17:11:37 +04:00
• 4058f51c02 Merge branch 'master' of https://github.com/iperov/DeepFaceLab iperov 2019-08-20 17:10:31 +04:00
• fc5efb559d upd readme iperov 2019-08-20 17:10:00 +04:00
• a33ef50da5 Long startup time on Linux (#356) Luke Barr 2019-08-19 13:56:54 -05:00
• e7562054d0 Fix sorting pathlib objects (#353) Auroir 2019-08-17 21:01:44 -07:00
• a906f24a4d Fix log_info/log_err printing with progress bars (#349) Auroir 2019-08-17 00:20:10 -07:00
• c4e68ef539 Formatted Model Summary (#348) Auroir 2019-08-16 07:35:27 -07:00
• 625bcc212d Return sorted filenames in path_utils (#340) Auroir 2019-08-12 07:18:55 -07:00
• d16759bcd3 ConverterMasked: added mask gradient of bottom area, same as side gradient iperov 2019-08-11 13:22:01 +04:00
• e8c5f168bd Merge branch 'master' of https://github.com/iperov/DeepFaceLab iperov 2019-08-11 11:17:38 +04:00
• b72d5a3f9a fixed error "Failed to get convolution algorithm" on some systems fixed error "dll load failed" on some systems Expanded eyebrows line of face masks. It does not affect mask of FAN-x converter mode. iperov 2019-08-11 11:17:22 +04:00
• e2bc65d5f0 Fix issue with RTX GPU and TensorFlow (#322) Josh Johnson 2019-08-02 13:40:41 +01:00
• 582c974851 Colab choose random preview (#316) fakerdaker 2019-07-25 03:29:31 -04:00
• d886cd79a8 upd readme Colombo 2019-07-15 15:27:51 +04:00
• 93ee889597 Identity is not the same thing as equality in Python (#291) cclauss 2019-06-27 19:10:22 +02:00
• 8484060e01 Trainer: added option for all models Enable autobackup? (y/n ?:help skip:%s) : Autobackup model files with preview every hour for last 15 hours. Latest backup located in model/<>_autobackups/01 iperov 2019-06-20 10:42:55 +04:00
• ea1d59f620 Update ModelBase.py (#283) Jakob6174 2019-06-19 10:02:19 +01:00
• fb9fd8c2b9
  Update README.md iperov 2019-06-19 12:24:11 +04:00
• 3d29130d5c
  closing the repo iperov 2019-06-13 08:38:09 +04:00
• ab8d03b4bb fix iperov 2019-06-02 19:20:06 +04:00
• c9da4cd89b fix for plaidML iperov 2019-05-24 09:30:39 +04:00
• 3114ae9d7b upd plaidml ver iperov 2019-05-20 22:42:34 +04:00
• 480360ba10 upd iperov 2019-05-18 23:43:40 +04:00