Commit Graph
100 Commits
Author SHA1 Message Date
AUTOMATIC1111andGitHub 6bd6154a92 Merge pull request #2067 from victorca25/esrgan_mod
update ESRGAN architecture and model to support all ESRGAN models
2022-10-23 13:43:41 +03:00
AUTOMATIC ca5a9e79dc fix for img2img color correction in a batch #3218 2022-10-22 22:06:54 +03:00
AUTOMATIC be748e8b08 add --freeze-settings commandline argument to disable changing settings 2022-10-22 22:05:22 +03:00
AUTOMATIC d213d6ca6f removed the option to use 2x more memory when generating previews
added an option to always only show one image in previews
removed duplicate code
2022-10-22 20:48:13 +03:00
AUTOMATIC 321bacc6a9 call model_loaded_callback after setting shared.sd_model in case scripts refer to it using that 2022-10-22 20:15:12 +03:00
AUTOMATIC 324c7c732d record First pass size as 0x0 for #3328 2022-10-22 20:09:51 +03:00
AUTOMATIC1111andGitHub ffea9b1509 Merge pull request #3414 from discus0434/master
[Hypernetworks] Add a feature to use dropout / more activation functions
2022-10-22 19:32:13 +03:00
AUTOMATIC dbc8ab65f6 typo 2022-10-22 19:19:17 +03:00
AUTOMATIC d37cfffd53 added callback for creating new settings in extensions 2022-10-22 19:18:56 +03:00
AUTOMATIC 7fd90128eb added a guard for hypernet training that will stop early if weights are getting no gradients 2022-10-22 14:48:43 +03:00
AUTOMATIC 1cd3ed7def fix for extensions without style.css 2022-10-22 14:28:56 +03:00
AUTOMATIC 50b5504401 remove parsing command line from devices.py 2022-10-22 14:04:14 +03:00
AUTOMATIC1111andGitHub e80bdcab91 Merge pull request #3377 from Extraltodeus/cuda-device-id-selection
Implementation of CUDA device id selection (--device-id 0/1/2)
2022-10-22 13:58:00 +03:00
AUTOMATIC1111andGitHub 1fa53dab2c Merge branch 'master' into cuda-device-id-selection 2022-10-22 13:57:20 +03:00
AUTOMATIC 5aa9525046 updated readme with info about Aesthetic Gradients 2022-10-22 13:40:07 +03:00
AUTOMATIC 6398dc9b10 further support for extensions 2022-10-22 13:34:49 +03:00
AUTOMATIC 2b91251637 removed aesthetic gradients as built-in
added support for extensions
2022-10-22 12:23:58 +03:00
AUTOMATIC 26d1073745 Merge remote-tracking branch 'historytab/master' 2022-10-21 18:49:56 +03:00
AUTOMATIC f49c08ea56 prevent error spam when processing images without txt files for captions 2022-10-21 18:46:02 +03:00
AUTOMATIC1111andGitHub 7464f367c3 Merge pull request #3246 from Milly/fix/train-preprocess-keep-ratio
Preprocess: fixed keep ratio and changed split behavior
2022-10-21 18:36:55 +03:00
AUTOMATIC1111andGitHub 5e9afa5c8a Merge branch 'master' into fix/train-preprocess-keep-ratio 2022-10-21 18:36:29 +03:00
AUTOMATIC 24ce67a13b make aspect ratio overlay work regardless of selected localization, pt2 2022-10-21 17:41:47 +03:00
AUTOMATIC ac0aa2b18e loading SD VAE, see PR #3303 2022-10-21 17:35:51 +03:00
AUTOMATIC 3d898044e5 batch_size does not affect job count 2022-10-21 17:26:30 +03:00
AUTOMATIC a7aa00d46a Merge remote-tracking branch 'mk2/outpainting-mk2-batch-out' 2022-10-21 17:22:47 +03:00
AUTOMATIC 704036ff07 make aspect ratio overlay work regardless of selected localization 2022-10-21 17:11:42 +03:00
AUTOMATIC1111andGitHub 3e12b5295c Merge pull request #3321 from AUTOMATIC1111/features-to-readme
Features to readme
2022-10-21 16:51:08 +03:00
AUTOMATIC1111andGitHub ec37f8a45f Merge branch 'master' into features-to-readme 2022-10-21 16:51:01 +03:00
AUTOMATIC 9286fe53de make aestetic embedding ciompatible with prompts longer than 75 tokens 2022-10-21 16:38:06 +03:00
AUTOMATIC e89e2f7c2c Merge remote-tracking branch 'origin/master' 2022-10-21 16:16:34 +03:00
AUTOMATIC df57064093 do not load aesthetic clip model until it's needed
add refresh button for aesthetic embeddings
add aesthetic params to images' infotext
2022-10-21 16:10:51 +03:00
AUTOMATIC 7d6b388d71 Merge branch 'ae' 2022-10-21 13:35:01 +03:00
AUTOMATIC bf30673f51 Fix Hypernet infotext string split bug for PR #3283 2022-10-21 10:19:25 +03:00
AUTOMATIC 03a1e288c4 turns out LayerNorm also has weight and bias and needs to be pre-multiplied and trained for hypernets 2022-10-21 10:13:24 +03:00
AUTOMATIC1111andGitHub e4877722e3 Merge pull request #3197 from AUTOMATIC1111/training-help-text
Training UI Changes
2022-10-21 09:58:16 +03:00
AUTOMATIC1111andGitHub 0c5522ea21 Merge branch 'master' into training-help-text 2022-10-21 09:57:55 +03:00
AUTOMATIC1111andGitHub 6c54532a34 Merge pull request #3263 from mezotaken/master
Fix skip and interrupt buttons for Highres. fix option enabled
2022-10-21 09:49:40 +03:00
AUTOMATIC1111andGitHub d6bd6a425d Merge branch 'master' into master 2022-10-21 09:49:32 +03:00
AUTOMATIC c23f666dba a more strict check for activation type and a more reasonable check for type of layer in hypernets 2022-10-21 09:47:43 +03:00
AUTOMATIC1111andGitHub a26fc2834c Merge pull request #3199 from discus0434/master
Add features to insert activation functions to hypernetworks
2022-10-21 09:34:45 +03:00
AUTOMATIC 12a97c5368 Merge remote-tracking branch 'origin/master' 2022-10-21 09:02:07 +03:00
AUTOMATIC 74088c2a06 allow float sizes for hypernet's layer_structure 2022-10-21 09:00:45 +03:00
AUTOMATIC 4587218190 updated readme and some small stylistic changes to code 2022-10-21 09:00:39 +03:00
AUTOMATIC 7f8ab1ee8f Merge remote-tracking branch 'origin/master' 2022-10-20 08:18:19 +03:00
AUTOMATIC 930b4c64f7 allow float sizes for hypernet's layer_structure 2022-10-20 08:18:02 +03:00
AUTOMATIC c6e9fed500 fix for #3086 failing to load any previous hypernet 2022-10-19 19:21:16 +03:00
AUTOMATIC1111andGitHub c664b231a8 Merge pull request #3162 from discus0434/master
Added what I forgot to commit in already merged PR: #3086
2022-10-19 18:58:49 +03:00
AUTOMATIC1111andGitHub f510a2277e Merge pull request #3086 from discus0434/master
Add settings for multi-layer structure hypernetworks
2022-10-19 18:40:53 +03:00
AUTOMATIC f894dd552f fix for broken checkpoint merger 2022-10-19 12:45:42 +03:00
AUTOMATIC 9931c0bd48 remove the unneeded line break introduced by #3092 2022-10-19 12:45:42 +03:00
AUTOMATIC1111andGitHub 1b91cbbc11 Merge pull request #2835 from zhengxiaoyao0716/hot-reload-javascript
hot-reload javascript files
2022-10-19 09:43:59 +03:00
AUTOMATIC1111andGitHub 05315d8a23 Merge branch 'master' into hot-reload-javascript 2022-10-19 09:43:49 +03:00
AUTOMATIC 5daf9cbb98 Merge remote-tracking branch 'origin/api' 2022-10-19 08:44:51 +03:00
AUTOMATIC 10aca1ca3e more careful loading of model weights (eliminates some issues with checkpoints that have weird cond_stage_model layer names) 2022-10-19 08:42:22 +03:00
AUTOMATIC cbf15edbf9 remove dependence on TQDM for sampler progress/interrupt functionality 2022-10-18 17:23:38 +03:00
AUTOMATIC ec1924ee57 additional fix for difference model merging 2022-10-18 16:05:52 +03:00
AUTOMATIC e20b7e30fe fix for add difference model merging 2022-10-18 15:33:32 +03:00
AUTOMATIC 433a7525c1 remove shared option for update check (because it is not an argument of webui)
have launch.py examine both COMMANDLINE_ARGS as well as argv for its arguments
2022-10-18 15:18:02 +03:00
AUTOMATIC d2f459c5cf clarify the comment for the new option from #2959 and move it to UI section. 2022-10-18 14:22:52 +03:00
AUTOMATIC1111andGitHub cd9c6e0edf Merge pull request #2984 from guaneec/D
Don't eat colons in booru tags
2022-10-18 14:18:05 +03:00
AUTOMATIC1111andGitHub c07dbd4cf9 Merge pull request #2939 from Michoko92/dark-mode
Added dark mode switch
2022-10-18 14:04:26 +03:00
AUTOMATIC1111andGitHub f6c758d055 Merge branch 'master' into dark-mode 2022-10-18 14:04:17 +03:00
AUTOMATIC cf47d13c1e localization support 2022-10-17 21:15:32 +03:00
AUTOMATIC 695377a8b9 make modelmerger work with ui-config.json 2022-10-17 19:56:23 +03:00
AUTOMATIC af3f6489d3 possibly defeat losing of focus for prompt when generating images with gallery open 2022-10-17 16:57:19 +03:00
AUTOMATIC d42125baf6 add missing requirement for api and fix some typos 2022-10-17 11:50:20 +03:00
AUTOMATIC 964b63c042 add api() function to return webui() to how it was 2022-10-17 11:38:32 +03:00
AUTOMATIC b99d3cf6dd make CLIP interrogate ranks output sane values 2022-10-17 08:41:02 +03:00
AUTOMATIC 5c94aaf290 fix bug for latest model merge RAM improvement 2022-10-17 08:28:18 +03:00
AUTOMATIC 6f7b7a3dcd only read files with .py extension from the scripts dir 2022-10-17 07:56:23 +03:00
AUTOMATIC c57919ea2a keep focus on current element when updating gallery 2022-10-16 17:22:56 +03:00
AUTOMATIC bd4f0fb9d9 revert changes to two bat files I asked to revert but the author couldn't in 863e9efc19. 2022-10-16 10:14:27 +03:00
AUTOMATIC 179e3ca752 honor --hide-ui-dir-config option for #2807 2022-10-16 09:51:01 +03:00
AUTOMATIC 0c5fa9a681 do not reload embeddings from disk when doing textual inversion 2022-10-16 09:09:04 +03:00
AUTOMATIC 74a9ee7002 fix saving images compatibility with gradio update 2022-10-15 20:09:45 +03:00
AUTOMATIC 73901c3f01 make attention edit only work with ctrl as was initially intended 2022-10-15 15:51:57 +03:00
AUTOMATIC 97f0727489 add First pass size always regardless of whether it was auto chosen or specified 2022-10-15 15:47:02 +03:00
AUTOMATIC 20a1f68c75 fix gadio issue with sending files between tabs 2022-10-15 15:44:46 +03:00
AUTOMATIC d3463bc59a change styling for top right corner UI
made save style button not die when you cancel
2022-10-15 14:22:30 +03:00
AUTOMATIC f7ca63937a bring back scale latent option in settings 2022-10-15 13:23:12 +03:00
AUTOMATIC 5967d07d1a fix new gradio failing to preserve image params 2022-10-15 13:11:28 +03:00
AUTOMATIC 3631adfe96 make dragging to prompt work again 2022-10-15 12:58:53 +03:00
AUTOMATIC e8729dd051 re-apply height hacks to work with new gradio 2022-10-15 12:54:23 +03:00
AUTOMATIC 4ed99d5996 bump gradio to 3.5 2022-10-15 12:10:52 +03:00
AUTOMATIC 7d6042b908 update for commandline args for btch prompts to parse string properly 2022-10-15 12:00:31 +03:00
AUTOMATIC1111andGitHub 58e62312c3 Merge pull request #1446 from shirase-0/master
Tag/Option Parsing in Prompts From File
2022-10-15 10:47:50 +03:00
AUTOMATIC1111andGitHub f42e0aae6d Merge branch 'master' into master 2022-10-15 10:47:26 +03:00
AUTOMATIC1111andGitHub d13ce89e20 Merge pull request #2573 from raefu/ckpt-cache
add --ckpt-cache option for faster model switching
2022-10-15 10:35:26 +03:00
AUTOMATIC1111andGitHub af144ebdc7 Merge branch 'master' into ckpt-cache 2022-10-15 10:35:18 +03:00
AUTOMATIC f756bc540a fix #2588 breaking launch.py (. . .) 2022-10-15 10:28:26 +03:00
AUTOMATIC1111andGitHub 9563636489 Merge pull request #2663 from space-nuko/fix-xyplot-steps
Fix XY-plot steps if highres fix is enabled
2022-10-15 10:20:29 +03:00
AUTOMATIC1111andGitHub 5207cba56f Merge pull request #2661 from Melanpan/master
Raise an assertion error if no training images have been found.
2022-10-15 10:13:23 +03:00
AUTOMATIC1111andGitHub ea8aa1701a Merge branch 'master' into master 2022-10-15 10:13:16 +03:00
AUTOMATIC c7a86f7fe9 add option to use batch size for training 2022-10-15 09:24:59 +03:00
AUTOMATIC acedbe67d2 bring history tab back, make it behave; it's still slow but won't fuck anything up until you use it 2022-10-15 00:43:15 +03:00
AUTOMATIC 4bbe5d62e0 reformat lines in images_history.py 2022-10-15 00:25:09 +03:00
AUTOMATIC 4dc4265099 rename firstpass w/h to discard old user settings 2022-10-15 00:21:48 +03:00
AUTOMATIC 368f4cc4c7 set firstpass w/h to 0 by default and rever to old behavior when any are 0 2022-10-14 23:19:05 +03:00
AUTOMATIC cd58e44051 disabling history - i knew it was slow as fuck but i didn't realize it would also show galleries on launch 2022-10-14 23:17:28 +03:00
AUTOMATIC 03d62538ae remove duplicate code for log loss, add step, make it read from options rather than gradio input 2022-10-14 22:43:55 +03:00