86d35526a1
make line evil again
3 years ago
1dd5d6bafa
clean py func defs
3 years ago
401350cd59
clear on the client-side again
3 years ago
25de9df364
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
910a097ae2
add initial version of the extensions tab
...
fix broken Restart Gradio button
3 years ago
840307f237
Change default clip grad value to 0.1
...
It still defaults to disabled.
Ref for value: 732b15820a
3 years ago
c9bb33dd43
add resrgan 8x, allow use 1x and up to 8x extra models, move BSRGAN model, add nearest
3 years ago
05e2e40537
Merge branch 'master' into gradient-clipping
3 years ago
35c45df28b
fix broken ↙ button, fix field paste ignoring most of useful fields for for #3768
3 years ago
28e6d4a54e
add element ids for save buttons for #3798
3 years ago
76086f6668
Merge branch 'master' into modal-save-button-and-shortcut
3 years ago
af547f63c3
Merge branch 'Inspiron'
3 years ago
3c207ca684
add needed imports fr new code in copypaste.py
3 years ago
a33d0a9a65
remove weird spaces added to ui.py over time
3 years ago
2d220afb24
fix open folder button not working
3 years ago
1fba573d24
Merge pull request #3874 from cobryan05/extra_tweak
...
Extras Tab - Option to upscale before face fix, caching improvements
3 years ago
bce5adcd6d
change default hypernet activation function to linear
3 years ago
1f1b327959
extras: Make image cache LRU
...
This changes the extras image cache into a Least-Recently-Used
cache. This allows more experimentation with different upscalers
without missing the cache.
Max cache size is increased to 5 and is cleared on source image
update.
3 years ago
26d0819384
extras: Add option to run upscaling before face fixing
...
Face restoration can look much better if ran after upscaling, as it
allows the restoration to fix upscaling artifacts. This patch adds
an option to choose which order to run upscaling/face fixing in.
3 years ago
16451ca573
Learning rate sched syntax support for grad clipping
3 years ago
1618df41ba
Gradient clipping for textual embedding
3 years ago
a133042c66
Forgot to remove this from train_embedding
3 years ago
2a25729623
Gradient clipping in train tab
3 years ago
268159cfe3
fixed indentation
3 years ago
0995e879ce
added save button and shortcut (s) to Modal View
3 years ago
e0cbf53f45
create send to buttons by extensions
3 years ago
85fcccc105
Squashed commit of fixing dropout silently
...
fix dropouts for future hypernetworks
add kwargs for Hypernetwork class
hypernet UI for gradio input
add recommended options
remove as options
revert adding options in ui
3 years ago
4a4647e0df
create send to buttons in one module
3 years ago
ee73341f04
Merge pull request #3139 from captin411/focal-point-cropping
...
[Preprocess image] New option to auto crop based on complexity, edges, faces
3 years ago
de096d0ce7
Weight initialization and More activation func
...
add weight init
add weight init option in create_hypernetwork
fstringify hypernet info
save weight initialization info for further debugging
fill bias with zero for He/Xavier
initialize LayerNorm with Normal
fix loading weight_init
3 years ago
df0c5ea29d
update default weights
3 years ago
db8ed5fe5c
Focal crop UI elements
3 years ago
6629446a2f
Merge branch 'master' into focal-point-cropping
3 years ago
cb9d2f8705
move to img component to public
3 years ago
994aaadf08
a strange bug
3 years ago
876a96f0f9
remove erroneous dir in the extension directory
...
remove loading .js files from scripts dir (they go into javascript)
load scripts after models, for scripts that depend on loaded models
3 years ago
a889c93f23
paste_fields add to public
3 years ago
cef1b89aa2
remove browser to extension
3 years ago
124e44cf1e
remove browser to extension
3 years ago
6a9ea40d7f
Move browser and Inspiration into extension
3 years ago
ce42879438
fix js func signature and not forget to initialize confirmation var to prevent exception upon cancelling confirmation
3 years ago
be748e8b08
add --freeze-settings commandline argument to disable changing settings
3 years ago
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
3 years ago
4fdb53c1e9
Generate grid preview for progress image
3 years ago
ffea9b1509
Merge pull request #3414 from discus0434/master
...
[Hypernetworks] Add a feature to use dropout / more activation functions
3 years ago
d37cfffd53
added callback for creating new settings in extensions
3 years ago
97749b7c7d
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
7912acef72
small fix
3 years ago
1cd3ed7def
fix for extensions without style.css
3 years ago
dcb45dfecf
Merge branch 'master' of upstream
3 years ago
0e8ca8e7af
add dropout
3 years ago
6398dc9b10
further support for extensions
3 years ago
2b91251637
removed aesthetic gradients as built-in
...
added support for extensions
3 years ago
700340448b
forgot to clear neg prompt after moving to back. Add tooltip to hints
3 years ago
0c7cf08b3d
some doc and formatting
3 years ago
9e40520f00
refactor internal terminology to use 'clear' instead of 'trash' like #2728
3 years ago
de70ddaf58
update token counter when clearing prompt
3 years ago
ee0505dd00
only delete prompt on back end and remove client-side deletion
3 years ago
9ba372de90
initial work on getting prompts cleared on the backend and synchronizing token counter
3 years ago
4a9ff0891a
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
bb0f1a2cda
inspiration finished
3 years ago
26d1073745
Merge remote-tracking branch 'historytab/master'
3 years ago
5e9afa5c8a
Merge branch 'master' into fix/train-preprocess-keep-ratio
3 years ago
704036ff07
make aspect ratio overlay work regardless of selected localization
3 years ago
df57064093
do not load aesthetic clip model until it's needed
...
add refresh button for aesthetic embeddings
add aesthetic params to images' infotext
3 years ago
7d6b388d71
Merge branch 'ae'
3 years ago
0c5522ea21
Merge branch 'master' into training-help-text
3 years ago
a3b047b7c7
add settings option to toggle button visibility
3 years ago
d07cb46f34
inspiration pull request
3 years ago
85dd62c4c7
train: ui: added `Split image threshold` and `Split image overlap ratio` to preprocess
3 years ago
f8733ad08b
add linear as a act func (option for doin nothing)
3 years ago
158d678f59
clear prompt button now works on both relevant tabs. Device detection stuff will be added later.
3 years ago
c6345bd445
nerf line length
3 years ago
ba469343e6
align ui.py imports with upstream
3 years ago
ecb433b220
update
3 years ago
6f98e89486
update
3 years ago
8b74b9aa9a
add symbol for clear button and simplify roll_col css selector
3 years ago
55d8c6cce6
default to ignore existing captions
3 years ago
ab353b141d
link existing txt option
3 years ago
4d6b9f76a5
reorder create_hypernetwork params
3 years ago
632e8d6602
split learn rates
3 years ago
4d663055de
update ui with extra training options
3 years ago
eb7ba4b713
update training header text
3 years ago
14c1c2b935
Show PB texts at same time and earlier
...
For big tasks (1000+ steps), waiting 1 minute to see ETA is long and this changes it so the number of steps done plays a role in showing the text as well.
3 years ago
1e4809b251
Added a bit of padding to the left
3 years ago
57eb1a64c8
Update ui.py
3 years ago
019a3a88f0
Update ui.py
3 years ago
365d4b1650
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
f510a2277e
Merge pull request #3086 from discus0434/master
...
Add settings for multi-layer structure hypernetworks
3 years ago
3770b8d2fa
enable to write layer structure of hn himself
3 years ago
42fbda83bb
layer options moves into create hnet ui
3 years ago
087609ee18
UI changes for focal point image cropping
3 years ago
2362d5f00e
Merge branch 'master' into test_resolve_conflicts
3 years ago
05315d8a23
Merge branch 'master' into hot-reload-javascript
3 years ago
1d4aa376e6
Predictable long operation check for time estimation
3 years ago
442dbedc15
Estimated time displayed if jobs take more 60 sec
3 years ago
bcfbb33e50
Added time left estimation
3 years ago
da72becb13
Use training width/height when training hypernetworks.
3 years ago
538bc89c26
Image browser improved
3 years ago
c2765c9bcd
Merge branch 'master' into test_resolve_conflicts
3 years ago
eb299527b1
Image browser
3 years ago
3003438088
Add visible for dropdown
3 years ago
de29ec0743
Remove exception handling
3 years ago
97d3ba3941
Add scripts to ui-config,json
3 years ago
8b02662215
Disable auto weights swap with config option
3 years ago
f6c758d055
Merge branch 'master' into dark-mode
3 years ago
1997ccff13
Merge branch 'master' into test_resolve_conflicts
3 years ago
7432b6f4d2
Fix typo "celem_id" to "elem_id"
3 years ago
ab3f997c0c
Fix typo in 'choices' when loading upscaler 2 config
3 years ago
cf47d13c1e
localization support
3 years ago
695377a8b9
make modelmerger work with ui-config.json
3 years ago
665beebc08
Use of a --theme argument for more flexibility
...
Added possibility to set the theme (light or dark)
3 years ago
8c6a981d5d
Added dark mode switch
...
Launch the UI in dark mode with the --dark-mode switch
3 years ago
589215df22
Merge branch 'master' into test_resolve_conflicts
3 years ago
c8045c5ad4
The hide_ui_dir_config flag also restrict write attempt to path settings
3 years ago
ae0fdad64a
Merge branch 'master' into test_resolve_conflicts
3 years ago
9324cdaa31
ui fix, re organization of the code
3 years ago
adc0ea74e1
Better readablity of logs
3 years ago
c9836279f5
Only make output dir when creating output
3 years ago
523140d780
ui fix
3 years ago
36a0ba357a
Added Refresh Button to embedding and hypernetwork names in Train Tab
...
Problem
everytime I modified pt files in embedding_dir or hypernetwork_dir, I
need to restart webui to have the new files shown in the dropdown of
Train Tab
Solution
refactored create_refresh_button out of create_setting_component so we
can use this method to create button next to gr.Dropdowns of embedding
name and hypernetworks
Extra Modification
hypernetwork pt are now sorted in alphabetic order
3 years ago
9258a33e37
Warn when user uses bad ui setting
3 years ago
b65a3101ce
Use default value when dropdown ui setting is bad
...
Default value is the first value of selectables.
Particually, None in styles.
3 years ago
20bf99052a
Make style configurable in ui-config.json
3 years ago
3395ba493f
Allow specifying the region of ngrok.
3 years ago
2ce27728f6
added extras batch work from directory
3 years ago
97ceaa23d0
Merge branch 'master' into test_resolve_conflicts
3 years ago
9a33292ce4
reload javascript files when custom script bodies
3 years ago
74a9ee7002
fix saving images compatibility with gradio update
3 years ago
3f5c3b981e
Update modules/ui.py
...
Co-authored-by: Víctor Gallego <vicgalle@ucm.es>
3 years ago
ad9bc604a8
Update modules/ui.py
...
Co-authored-by: Víctor Gallego <vicgalle@ucm.es>
3 years ago
0d4f5db235
Update modules/ui.py
...
Co-authored-by: Víctor Gallego <vicgalle@ucm.es>
3 years ago
4387e4fe64
Update modules/ui.py
...
Co-authored-by: Víctor Gallego <vicgalle@ucm.es>
3 years ago
7b7561f6e4
Merge branch 'master' into test_resolve_conflicts
3 years ago
5fd638f14d
fix download section layout
3 years ago
37d7ffb415
fix to tokens lenght, addend embs generator, add new features to edit the embedding before the generation using text
3 years ago
20a1f68c75
fix gadio issue with sending files between tabs
3 years ago
d3463bc59a
change styling for top right corner UI
...
made save style button not die when you cancel
3 years ago
5967d07d1a
fix new gradio failing to preserve image params
3 years ago
e8729dd051
re-apply height hacks to work with new gradio
3 years ago
db27b987a9
Add hint for `ctrl/alt enter`
...
And duplicate implementations are removed
3 years ago
c7a86f7fe9
add option to use batch size for training
3 years ago
acedbe67d2
bring history tab back, make it behave; it's still slow but won't fuck anything up until you use it
3 years ago
4dc4265099
rename firstpass w/h to discard old user settings
3 years ago
368f4cc4c7
set firstpass w/h to 0 by default and rever to old behavior when any are 0
3 years ago
cd58e44051
disabling history - i knew it was slow as fuck but i didn't realize it would also show galleries on launch
3 years ago
03d62538ae
remove duplicate code for log loss, add step, make it read from options rather than gradio input
3 years ago
326fe7d44b
Merge remote-tracking branch 'Melanpan/master'
3 years ago
c250cb289c
change checkpoint merger to work in a more obvious way
...
remove sigmoid and inverse sigmoid because they just did the same thing as weighed sum only with changed multiplier
3 years ago
c344ba3b32
add option to read generation params for learning previews from txt2img
3 years ago
6b77af7a43
Merge pull request #2396 from yfszzx/master
...
Add a "History" tab
3 years ago
67f447ddcc
possibility to load checkpoint, clip skip, and hypernet from infotext
3 years ago
0aec19d783
make pasting into img2img prompt work
...
make image params request not use temp files
3 years ago
a156c097ab
Merge branch 'param-loading'
3 years ago
e644b5a80b
remove scale latent and no-crop options from hires fix
...
support copy-pasting new parameters for hires fix
3 years ago
40d1c6e423
Option between stretch and crop for Highres. fix
3 years ago
b2261b53ae
Added first_pass_width and height as adjustable inputs to "High Res Fix"
3 years ago
bb57f30c2d
init
3 years ago
f7712e28e5
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
fdecb63685
add an ability to merge three checkpoints
3 years ago
7c8903367c
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
08b3f7aef1
emergency fix for broken send to buttons
3 years ago
354ef0da3b
add hypernetwork multipliers
3 years ago
a10b0e11fc
options to refresh list of models and hypernetworks
3 years ago
bb7baf6b9c
add option to change what's shown in quicksettings bar
3 years ago
fed7f0e281
Revert "fix prompt in log.csv"
...
This reverts commit e4b5d1696429ab78dae9779420ce6ec4cd9c5f67.
3 years ago
a3f02e4690
fix prompt in log.csv
3 years ago
8711c2fe01
Fix metadata contents
3 years ago
aeacbac218
Fix save error
3 years ago
0186db178e
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
54e0051bdd
Add drag/drop param loading.
...
Drop an image or generational text onto the prompt bar, it loads the info for parsing.
3 years ago
1cfc2a1898
Save a csv containing the loss while training
3 years ago
698d303b04
deepbooru: added option to use spaces or underscores
...
deepbooru: added option to quote (\) in tags
deepbooru/BLIP: write caption to file instead of image filename
deepbooru/BLIP: now possible to use both for captions
deepbooru: process is stopped even if an exception occurs
3 years ago
c3c8eef9fd
train: change filename processing to be more simple and configurable
...
train: make it possible to make text files with prompts
train: rework scheduler so that there's less repeating code in textual inversion and hypernets
train: move epochs setting to options
3 years ago
324e6ed5d1
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
a1a94b8b5f
images history improvement
3 years ago
c87c3b9c11
test
3 years ago
cc5803603b
Merge pull request #2037 from AUTOMATIC1111/embed-embeddings-in-images
...
Add option to store TI embeddings in png chunks, and load from same.
3 years ago
ee015a1af6
change textual inversion tab to train
...
remake train interface to use tabs
3 years ago
dc1432e0dd
Merge branch 'master' into feature/scale_to
3 years ago
57e03cdd24
Ensure the directory exists before saving to it
...
The directory for the images saved with the Save button may still not exist, so it needs to be created prior to opening the log.csv file.
3 years ago
2e2d45b281
Merge pull request #2143 from JC-Array/deepdanbooru_pre_process
...
deepbooru tags for textual inversion preproccessing
3 years ago
fec2221eea
Truncate error text to fix service lockup / stall
...
What:
* Update wrap_gradio_call to add a limit to the maximum amount of text output
Why:
* wrap_gradio_call currently prints out a list of the arguments provided to the failing function.
* if that function is save_image, this causes the entire image to be printed to stderr
* If the image is large, this can cause the service to lock up while attempting to print all the text
* It is easy to generate large images using the x/y plot script
* it is easy to encounter image save exceptions, including if the output directory does not exist / cannot be written to, or if the file is too big
* The huge amount of log spam is confusing and not particularly helpful
3 years ago
f53f703aeb
resolved conflicts, moved settings under interrogate section, settings only show if deepbooru flag is enabled
3 years ago
963d986396
Merge branch 'AUTOMATIC1111:master' into deepdanbooru_pre_process
3 years ago
d6fcc6b87b
apply lr schedule to hypernets
3 years ago
419e539fe3
Merge branch 'learning_rate-scheduling' into learnschedule
3 years ago
d682444ecc
add option to select hypernetwork modules when creating
3 years ago
f7e86aa420
Merge pull request #2227 from papuSpartan/master
...
Refresh list of models/ckpts upon hitting restart gradio in the setti…
3 years ago
1eaad95533
Merge branch 'master' into embed-embeddings-in-images
3 years ago
d01a2d0156
move list refresh to webui.py and add stdout indicating it's doing so
3 years ago
a36dea9596
Merge branch 'master' into master
3 years ago
b0583be088
more renames
3 years ago
873efeed49
rename hypernetwork dir to hypernetworks to prevent clash with an old filename that people who use zip instead of git clone will have
3 years ago
5992564448
Cleaned ngrok integration
3 years ago
861297cefe
add a space holder
3 years ago
87b77cad5f
Layout fix
3 years ago
594ab4ba53
images history improvement
3 years ago
530103b586
fixes related to merge
3 years ago
5de806184f
Merge branch 'master' into hypernetwork-training
3 years ago
8617396c6d
Added slider for deepbooru score threshold in settings
3 years ago
8b7d3f1bef
Make the ctrl+enter shortcut use the generate button on the current tab
3 years ago
1add3cff84
Refresh list of models/ckpts upon hitting restart gradio in the settings pane
3 years ago
47f5e216da
Merge branch 'deepdanbooru_pre_process' into master
3 years ago
2536ecbb17
Refactored learning rate code
3 years ago
1d64976dbc
Simplify crop logic
3 years ago
9d33baba58
Always show previous mask and fix extras_send dest
3 years ago
f347ddfd80
Remove max_batch_count from ui.py
3 years ago
ce2d7f7eac
Merge branch 'master' into embed-embeddings-in-images
3 years ago
7a20f914ed
Custom Width and Height
3 years ago
ea00c1624b
Textual Inversion: Added custom training image size and number of repeats per input image in a single epoch
3 years ago
1e18a5ffcc
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
23f2989799
images history over
3 years ago
2f94331df2
removed change in last commit, simplified to adding the visible argument to process_caption_deepbooru and it set to False if deepdanbooru argument is not set
3 years ago
8ec069e64d
removed duplicate run_preprocess.click by creating run_preprocess_inputs list and appending deepbooru variable to input list if in scope
3 years ago
8a7c07a214
show image history
3 years ago
1f92336be7
refactored the deepbooru module to improve speed on running multiple interogations in a row. Added the option to generate deepbooru tags for textual inversion preproccessing.
3 years ago
6435691bb1
Add "Scale to" option to Extras
3 years ago
4117afff11
Merge branch 'master' into embed-embeddings-in-images
3 years ago
6c383d2e82
show model selection setting on top of page
3 years ago
6f6798ddab
prevent a possible code execution error (thanks, RyotaK)
3 years ago
ab4fe4f44c
hide filenames for save button by default
3 years ago
e00b4df7c6
Merge pull request #1752 from Greendayle/dev/deepdanbooru
...
Added DeepDanbooru interrogator
3 years ago
14192c5b20
Support `Download` for txt files.
3 years ago
5ab7e88d9b
Add `Download` & `Download as zip`
3 years ago
cd8673bd9b
add embed embedding to ui
3 years ago
432782163a
chore: Fix typos
3 years ago
b458fa48fe
Update ui.py
3 years ago
15c4278f1a
TI preprocess wording
...
I had to check the code to work out what splitting was 🤷🏿
3 years ago
01f8cb4447
made deepdanbooru optional, added to readme, automatic download of deepbooru model
3 years ago
2e8ba0fa47
fix conflicts
3 years ago
4f33289d0f
Fixed typo
3 years ago
786d9f63aa
Add button to skip the current iteration
3 years ago
12c4d5c6b5
hypernetwork training mk1
3 years ago
537da7a304
Merge branch 'master' into dev/deepdanbooru
3 years ago
0bb458f0ca
Removed duplicate image saving codes
...
Use `modules.images.save_image()` instead.
3 years ago
c26732fbee
added support for AND from https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/
3 years ago
59a2b9e5af
deepdanbooru interrogator
3 years ago
bbdbbd36ed
shared.state.interrupt when restart is requested
3 years ago
ef40e4cd4d
Display time taken in mins, secs when relevant
...
Fixes #1656
3 years ago
b32852ef03
add editor to img2img
3 years ago
d5bba20a58
ignore errors in parse for purposes of token counting for #1564
3 years ago
43a74fa595
batch processing for img2img with an empty output directory, by request
3 years ago
e615d4f9d1
Convert folder icon surrogate pair to valid utf8
3 years ago
6785331e22
keep textual inversion dataset latents in CPU memory to save a bit of VRAM
3 years ago
c7543d4940
preprocessing for textual inversion added
3 years ago
91f327f22b
make save to dirs optional for imgs saved from ui
3 years ago
688c4a914a
Merge branch 'master' into 1404-script-reload-without-restart
3 years ago
e808096cf6
correct indent
3 years ago
0b94fc5033
Merge pull request #1324 from liamkerr/token_updates
...
Fixing Bugs with Token Counter
3 years ago
papuSpartan
papuSpartan
AUTOMATIC
Muhammad Rizqi Nur
victorca25
Chris OBryan
Florian Horn
yfszzx
AngelBottomless
captin411
Unnoen
discus0434
discus0434
Milly
DepFA
Alexandre Simard
MalumaDev
Anastasius
Silent
ふぁ
trufty
Mykeehu
Jordan Hall
Michoko
SGKoishi
CookieHCl
Junpeng Qiu
ddPn08
winterspringsummer
zhengxiaoyao0716
ruocaled
aoirusann
Buckzor
Greg Fuller
d8ahazard
Melan
brkirch
JC_Array
JC-Array
JamnedZ
Ben
Kenneth
Jairo Correa
Fampai
Justin Maier
Vladimir Repin
RW21
alg-wiki
aoirusann
Aidan Holland
Greendayle
Trung Ngo
xpscyho
Hanusz Leszek
Lopyter