Commit Graph

160 Commits (58f620c921030eea0f3528d68849f7e052d44e3f)

Author SHA1 Message Date
Chenlei Hu 17e100e1fe
Revert "Port DW Pose preprocessor (#1856)" (#1860)
This reverts commit 0d3310f599.
2023-08-04 15:13:51 -04:00
Chenlei Hu 0d3310f599
Port DW Pose preprocessor (#1856)
*  Add dependencies

* 🚧 wip

* 🚧 wip

* 🚧 download models

* 🚧 Minor fixes

* 🔧 update gitignore

* 🐛 Fix normalization issue

* 🚧 load DW model only when DW preprocessor is selected

*  Change test config

* 🎨 nits

* 🐛 Fix A1111 safe torch issue
2023-08-04 15:02:58 -04:00
Leye Hu 5fc952793a
fix: runtime error for directml in pidinet (#1654) 2023-06-18 13:43:46 -04:00
lingyu.hai 9789d097fe fix runtime error for multi gpu in pidinet 2023-06-13 15:05:21 +08:00
lllyasviel 69f5760a32
fix dependency (#1595)
* fix dependency

* fix dependency
2023-06-08 17:50:56 -07:00
lllyasviel 34df0a3374
prepare for future preprocessors (#1552) 2023-06-04 14:18:05 -07:00
Chenlei Hu 5b681b071b
New feature: integrated openpose editor (#1454)
🎨 nits

🎨 Load alert screen when no editor is detected.

🔧 add option to hide edit button

🐛 Resolve conflicts during rebase

🚧 Set use preview as input after edit

🐛 Fix merge conflict
2023-06-04 15:54:35 -04:00
lvmin 9985eafc19 remove old codes 2023-05-06 10:48:04 -07:00
lvmin 99008f6b86 rename 2023-05-06 10:32:50 -07:00
lvmin a57a8f71e0 fix all ratio problems 2023-05-06 10:27:17 -07:00
huchenlei 1c1ff7b7d5 📝 Replace pipe operator on type annotation with 3.8 compatible syntax 2023-05-02 16:26:32 -04:00
huchenlei 99820f8db7 📝 Use 3.8 compatible syntax 2023-05-02 16:13:24 -04:00
huchenlei a96b98e4fc 📝 add back type annotation on BodyResult 2023-05-02 13:48:38 -04:00
lvmin 53e5bb4d6f remove dangerous options, add leres++ 2023-05-02 01:29:01 -07:00
lvmin f715763d9e fix strange openpose problem 2023-05-02 00:30:36 -07:00
lvmin e07a547412 fix leres 2023-05-01 22:03:07 -07:00
camenduru b0e1521ca1
cloudstor.aarnet.edu.au -> 429 Too Many Requests 2023-05-01 22:26:48 +03:00
lvmin cac93c33d5 openpose license 2023-05-01 03:57:54 -07:00
lvmin 3289105e96 fix openpose mistake 2023-05-01 03:28:22 -07:00
lvmin 65e0218b9e fix openpose mistake 2023-05-01 03:27:32 -07:00
lvmin 19eb215c0f fix openpose mistake 2023-05-01 03:22:53 -07:00
huchenlei c700483928 Add download json button 2023-04-30 21:13:06 -04:00
huchenlei e6b6993b6d 🐛 handles np float types when serializing JSON 2023-04-28 22:05:09 -04:00
huchenlei 3875a16abe Add json encoding logic 2023-04-28 17:35:50 -04:00
huchenlei afc27c0c26 Add documentation 2023-04-28 16:52:11 -04:00
huchenlei 09296b1684 Refactor openpose data representation 2023-04-28 16:30:04 -04:00
lvmin 1f1a9e135d fix 2023-04-26 19:46:55 -07:00
Arron17 c9d32787da Adding Manga Line Extraction Processor
Adding initial working Manga Line Extraction Processor from https://github.com/ljsabc/MangaLineExtraction_PyTorch
2023-04-26 21:46:30 +01:00
lllyasviel 655192ad86
Change requested by an important anonymous user
Change requested by an important anonymous user
2023-04-22 20:15:06 -07:00
ljleb 3ff63befce
Add command line arguments to readme (#933)
* relative path is relative to webui

* docs

* change default path back to webui/models

* for now, revert model path change
2023-04-20 11:26:38 -04:00
lvmin b6f6588417 add licenses 2023-04-19 21:29:52 -07:00
lvmin f4cd2d51f6 use ControlNetHED with Apache License 2.0 2023-04-19 16:04:58 -07:00
lvmin 238c8cd8f1 improve inpaint mask quality 2023-04-19 01:19:40 -07:00
lvmin 483450add6 fix 90% amd problems 2023-04-19 00:37:20 -07:00
lvmin d62badd9d1 add sanity check to log so that reading github issue is easier 2023-04-18 09:06:55 -07:00
lvmin 3d3555b960 add sanity check to log so that reading github issue is easier 2023-04-18 09:05:34 -07:00
lvmin ea2c16bf74 add sanity check to log so that reading github issue is easier 2023-04-18 08:54:26 -07:00
ljleb 804d32ee3f add options 2023-04-18 06:16:59 -04:00
lvmin 57b95a3a78 better module 2023-04-18 00:21:29 -07:00
lvmin 78ad101279 include downloads for clip vison fix2 2023-04-17 23:44:56 -07:00
lvmin c0059da198 include downloads for clip vison 2023-04-17 23:42:06 -07:00
lvmin 1d07f5ebd7 change annotator paths so that users can remove all when corrupted 2023-04-17 22:48:00 -07:00
lvmin 42158b1b43 major update - ControlNet 1.1 GUI 2023-04-17 16:53:20 -07:00
Joseph Catrambone 385b67c2e3 Merge upstream changes and resolve merge conflicts. 2023-04-17 09:35:49 -07:00
lvmin efee5fe399 remove buggy pycocotools 2023-04-15 11:40:35 -07:00
Mikubill f5eb9bd080 i 2023-04-15 08:11:52 +00:00
Mikubill 920c948ec0 fix: remove large txt file (of) 2023-04-15 08:05:29 +00:00
Mikubill b7a2058419 fix: deprec thr-based inversion (and #736), cleanup code 2023-04-15 07:41:26 +00:00
RcINS b1c0bc62e0 Add {lineart, lineart_anime, normalbae, oneformer, shuffle, zoe} annotator 2023-04-13 18:01:29 +08:00
Joseph Catrambone 603449ce48 Clarify error message and remove PIL import. 2023-03-31 12:07:44 -07:00
Joseph Catrambone 132bcb4dc9 Since we're already diverging from the original, might as well remove vestigial annotation stuff. 2023-03-31 11:39:37 -07:00
Joseph Catrambone 51cbd171f4 Default to 0.5 confidence. Handle an edge case where result set is null rather than empty. 2023-03-31 11:33:15 -07:00
Joseph Catrambone 4adb9a38b9 Make min_confidence a required parameter. Change the default max faces to 10. 2023-03-31 11:26:54 -07:00
Joseph Catrambone 42a25e0b5c Update UI to allow number of faces and confidence to be selected. 2023-03-31 10:57:10 -07:00
Joseph Catrambone 3cd07a6ee8 Rename mediapipe_laion_face to mediapipe_face. 2023-03-31 10:48:17 -07:00
Joseph Catrambone f4d728539c Move the copy from controlnet's internals back into laion_face_common to see if we can alleviate the negative stride without changing the codebase. 2023-03-31 10:31:55 -07:00
Joseph Catrambone a2c1561c1f Fix processor script + init to correctly generate processed face. 2023-03-30 17:12:03 -07:00
Joseph Catrambone 78833dce35 Add MediaPipe Face conditioning as a step. 2023-03-30 16:30:41 -07:00
Mikubill 5dfdc772d4 fix: resize issue with t2i-adapter/color alignment 2023-03-08 03:52:21 +00:00
Mikubill 84274a1388 fix: move pidinet to correct device 2023-03-07 02:33:28 +00:00
Mikubill 6a425582e9 fix: add more fallbacks for mmpkg (#510) 2023-03-06 13:18:28 +00:00
Yoshitada Kurozumi b49d3375ca Add binary preprocessor 2023-03-06 01:09:34 +09:00
Kakigōri Maker eab5bc08cb
Merge pull request #479 from catboxanon/new-t2i-adapters
Support for new T2I adapters (color, style)
2023-03-05 23:50:54 +09:00
Mikubill cdc807ad55 feat: add color annotator, minor fix 2023-03-05 04:54:18 +00:00
Mikubill 9acfb6d89e feat: add clip_vision annotator, support non-image input 2023-03-05 04:27:36 +00:00
Mikubill 2ff1154f46 fix: module registration issue (#488) 2023-03-04 16:30:56 +00:00
Mikubill eb84fd9c59 fix: add mmcv fallback - revert 6dea4af 2023-03-04 15:07:06 +00:00
Mikubill 6dea4af076 fix: remove mmcv packages, prepare for new annotator/models 2023-03-04 10:14:10 +00:00
AO 63223e5261
fix(uniformer) fix model loading path 2023-02-23 22:34:52 +01:00
Nerdy Rodent 2397a6c884
Add files via upload 2023-02-23 08:43:57 +00:00
Mikubill 9831aa3006 fix: move leres model to correct device (#293) 2023-02-22 15:20:10 +00:00
Mikubill f4f51abd3c fix: add fallback path 2023-02-22 14:20:25 +00:00
missionfloyd ca88ccd8ed
Merge branch 'main' into model-path 2023-02-21 22:37:45 -07:00
Mikubill caa56b7dc6 minor fix and #276 2023-02-22 04:07:12 +00:00
missionfloyd 698e136093
Merge branch 'main' into model-path 2023-02-20 21:48:29 -07:00
Mikubill 3ccc1fd01e fix: move depth_boosting to settings 2023-02-21 03:25:29 +00:00
Mikubill b1dbf0a048 cleanup 2023-02-21 11:53:17 +09:00
Kakigōri Maker 0b55af6cee
Merge branch 'main' into main 2023-02-21 11:50:11 +09:00
wbh1129 85156dcdf9
fix: use CUDA only if available for leres 2023-02-20 20:09:39 -06:00
Chris Mekarski bcec70c378 Fix imports 2023-02-20 18:39:17 -05:00
Mikubill c6fc96eef9 feat: add guess_mode and cfg_based guidance 2023-02-20 15:20:59 +00:00
Chris Mekarski 030922a3d2 Add depth boost
https://github.com/compphoto/BoostingMonocularDepth
2023-02-19 20:52:00 -05:00
missionfloyd b62873196c
Merge branch 'main' into model-path 2023-02-18 20:47:41 -07:00
Chris Mekarski d32907b90a Add LICENSE 2023-02-18 20:16:53 -05:00
missionfloyd 453424fe21 Separate annotator folders 2023-02-18 15:39:15 -07:00
missionfloyd 842f2a5ab5 Update leres path 2023-02-18 14:54:30 -07:00
missionfloyd 7dd91595d1
Merge branch 'Mikubill:main' into model-path 2023-02-18 14:50:47 -07:00
Chris Mekarski 5620c1cd5a Add LeReS depth thresholds and cleanup
Adds near and background removal/thresholds
Adds CPU model loading
Increase default model res to 512
Pass image dimensions to model
Remove duplicate functions in utils.py
2023-02-18 14:02:13 -05:00
missionfloyd a8b1e79b9b Remove unused ckpts folder 2023-02-17 21:53:28 -07:00
missionfloyd e1ff318d72 Move annotators 2023-02-17 15:48:27 -07:00
Chris Mekarski 5048c4c9f1 Add support for LeReS 2023-02-17 14:27:29 -05:00
Mikubill eca48855f8 merge conflict 2023-02-17 15:03:39 +00:00
Kakigōri Maker 3484a30b94
Merge pull request #94 from eltociear/patch-1
chore: fix typo in metrics.py
2023-02-17 23:35:48 +09:00
Mikubill 0146699545 feat: impl t2i-adapter 2023-02-17 11:40:19 +00:00
Kakigōri Maker 7a427668c8
Revert "use relative path for download directory" 2023-02-17 01:26:13 +09:00
Luo Boming 4b8dea44af use relative path for download directory 2023-02-17 00:07:18 +09:00
Aarni Koskela 47092d69a2 Patch out prettytable requirement 2023-02-16 16:38:47 +02:00
Ikko Eltociear Ashimine df1c200779
chore: fix typo in metrics.py
Wether -> Whether
2023-02-16 21:15:29 +09:00
brkirch 601192b7f3 Use CPU, not MPS for depth/normal map preprocessor
Use CPU instead of MPS for the depth/normal map preprocessor model to workaround the bugs in MPS that produce corrupted depth and normal maps.

Also included here is a change to `unload_midas_model()` to fix not sending the model to CPU.
2023-02-16 01:49:24 -05:00
Mikubill c7c9f936d0 fix: unload models when switching preprocessor 2023-02-15 13:03:35 +00:00