1a50272e7c
revert some questionable changes from #9159
2023-04-29 17:45:22 +03:00
88c7debb02
Merge branch 'dev' into ui-config-tabs
2023-04-29 17:42:57 +03:00
78d0ee3bba
Merge branch 'dev' into extension-settings-backup
2023-04-29 17:22:24 +03:00
8987764395
Merge pull request #9312 from space-nuko/save-merge-recipe
...
Embed model merge metadata in .safetensors file
2023-04-29 17:15:01 +03:00
3894609b52
Merge branch 'dev' into master
2023-04-29 17:02:14 +03:00
17cce45613
Merge pull request #8948 from hitomi/master
...
Fix --realesrgan-models-path and --ldsr-models-path not working
2023-04-29 17:00:24 +03:00
f2af6dad71
Merge pull request #9351 from nart4hire/fix-ngrok-recreate-tunnel
...
Fix Ngrok recreating tunnels every reload
2023-04-29 16:56:20 +03:00
78b5bed374
Merge pull request #9407 from GoulartNogueira/master
...
Fix orientation bug on preprocess
2023-04-29 16:53:17 +03:00
1142a87c6a
Merge pull request #9219 from Z-nonymous/master
...
Fix #9185
2023-04-29 16:52:39 +03:00
263f0fb59c
Merge branch 'dev' into remove-watermark-option
2023-04-29 16:50:52 +03:00
faff08f396
rework [batch_number]/[generation_number] filename patterns
2023-04-29 16:48:43 +03:00
e7d624574d
Merge branch 'dev' into master
2023-04-29 16:41:01 +03:00
7428fb5176
add is_hr_pass field for processing
2023-04-29 16:28:51 +03:00
e10ee96272
Merge pull request #9334 from gmasil/prepare-simpler-docker-integration-for-styles-csv
...
allow styles.csv to be symlinked or mounted in docker
2023-04-29 16:14:55 +03:00
8863b31d83
use correct images for previews when using AND (see #9491 )
2023-04-29 16:06:20 +03:00
737b73a820
some extra lines I forgot to add for previous commit
2023-04-29 16:05:20 +03:00
1d11e89698
rework Negative Guidance minimum sigma to work with AND, add infotext and copypaste parameters support
2023-04-29 15:57:09 +03:00
3591eefedf
Merge pull request #9177 from devNegative-asm/master
...
(Optimization) Option to remove negative conditioning at low sigma values
2023-04-29 14:38:25 +03:00
fdac486835
Merge pull request #9484 from infinitewarp/sort-embeddings
...
sort embeddings by name (case insensitive)
2023-04-29 14:03:02 +03:00
cb940a583d
fix extension installation broken by #9518
2023-04-29 13:45:14 +03:00
32c3b97669
Merge pull request #9628 from catboxanon/patch/9092
...
Fix image mask/composite for weird resolutions
2023-04-29 13:21:32 +03:00
87535fcf29
Merge branch 'dev' into Branch_AddNewFilenameGen
2023-04-29 13:10:46 +03:00
d6a3988b86
Merge pull request #9669 from catboxanon/patch/sampler-schedule-fix
...
Fix prompt schedule for second order samplers
2023-04-29 12:56:57 +03:00
fc6eeda69c
Merge pull request #9130 from Vespinian/fix-api-alwayson_scripts-less-then-requiered-args
...
[Fix] Prevent alwayson_scripts args param resizing script_arg list when they are inserted in it
2023-04-29 12:55:19 +03:00
b06205eaf6
Allow user input for gradio theme selection
2023-04-29 12:52:09 +03:00
e6cbfcfe5b
Merge branch 'dev' into gradio-theme-support
2023-04-29 12:45:43 +03:00
2c935d8eb0
Merge pull request #9518 from yike5460/master
...
add branch support for extension installation
2023-04-29 12:41:30 +03:00
ee71eee181
stuff related to torch version change
2023-04-29 12:36:50 +03:00
e55cb92067
Merge pull request #9737 from AdjointOperator/master
...
add tiled inference support for ScuNET
2023-04-29 11:34:35 +03:00
5fe0dd79be
rename CPU RNG to RNG source in settings, add infotext and parameters copypaste support to RNG source
2023-04-29 11:29:37 +03:00
cb9571e37f
Merge pull request #9734 from deciare/cpu-randn
...
Option to make images generated from a given manual seed consistent across CUDA and MPS devices
2023-04-29 11:16:06 +03:00
dda839f686
Merge pull request #9693 from racinmat/hidable_buttons
...
adds label to buttons to make them hide
2023-04-29 11:05:51 +03:00
1f6aabbd55
Merge pull request #9839 from dennissheng/master
...
fix ui img2img scripts
2023-04-29 10:26:47 +03:00
5b4bcea956
Merge pull request #9757 from missionfloyd/editattention-selectcurrentword
...
Automatically select current word when adjusting weight with ctrl+up/down
2023-04-29 10:05:37 +03:00
642d96dcc8
use exist_ok=True instead of checking if directory exists
2023-04-29 10:04:01 +03:00
39654cc905
Merge pull request #9867 from darnell8/master
...
Fix CLIP FileExistsError
2023-04-29 10:03:07 +03:00
b0f55d374e
Merge pull request #9429 from forsurefr/save-init-images
...
Add support for saving init images in img2img
2023-04-29 10:01:33 +03:00
cf5bd93200
Merge pull request #9657 from Filexor/master
...
Add filename pattern for CLIP_stop_at_last_layers (clip skip).
2023-04-29 09:43:43 +03:00
1514add559
remove unneded imports and type signature
2023-04-29 09:42:49 +03:00
37c59c2710
Merge pull request #9723 from missionfloyd/extra-network-none
...
Add "None" option to extra networks dropdowns
2023-04-29 09:42:07 +03:00
a33d49cc57
Merge branch 'dev' into fix_batch_processing
2023-04-29 09:30:33 +03:00
5a666f3904
bump gradio to 3.27
2023-04-29 09:21:31 +03:00
101a18fc84
bump gradio to 3.27
2023-04-29 09:17:35 +03:00
aac478cb9d
Should be "utils"
2023-04-27 21:40:16 -04:00
ed46abea35
fix for method moved to gradio_client
2023-04-27 21:30:55 -04:00
d1e62b2961
Improve param semantics,
2023-04-27 21:30:19 -04:00
43186ad084
Add tls_verify arg for use with self-signed certs
2023-04-27 20:29:21 -04:00
bb426de1cd
Fix CLIP FileExistsError
2023-04-25 22:53:06 +08:00
b2f6e0704e
add subpath support
2023-04-25 07:27:24 -07:00
0e071ae504
Custom delimiters
2023-04-25 08:08:57 -06:00
bbc7a778d8
fix ui img2img scripts
2023-04-24 17:36:16 +08:00
eff00413ae
Refresh bug fix
2023-04-21 12:34:38 +08:00
988dd02632
Add img2img refreshed correctly
2023-04-20 15:09:19 +08:00
2c24e09dfc
Fix gallery not being refreshed correctly
2023-04-20 14:53:37 +08:00
dec5cdd9b8
add tiled inference support for ScuNET
2023-04-19 15:35:50 +08:00
d40e44ade4
Option to use CPU for random number generation.
...
Makes a given manual seed generate the same images across different
platforms, independently of the GPU architecture in use.
Fixes #9613 .
2023-04-18 23:27:46 -04:00
f4b332f041
Add "None" option to extra networks dropdowns
2023-04-18 17:01:46 -06:00
eddcdb8061
adds label to buttons to make them hide
2023-04-17 23:48:28 +02:00
3e5b3c79e4
replace with #wrap_session_call
2023-04-17 13:53:41 +08:00
9de7298898
Update processing.py
2023-04-16 21:06:37 -04:00
234fa9a57d
Update shared.py
2023-04-16 21:06:22 -04:00
4d0c816303
Modify step multiplier flow
2023-04-16 20:39:45 -04:00
81b276a1ea
Add second order samplers compat option
2023-04-16 20:39:18 -04:00
56f8a6b081
Fix sampler schedules with step multiplier
2023-04-16 20:34:52 -04:00
984970068c
multi users support
2023-04-17 01:06:28 +08:00
acbec22554
Add self argument that is mandatory to [clip_skip] filename pattern.
2023-04-16 17:14:11 +09:00
596556162e
Add filename pattern for CLIP_stop_at_last_layers.
2023-04-16 16:49:21 +09:00
02e3518807
Add new FilenameGenerator [hasprompt<prompt1|default><prompt2>..]
2023-04-15 23:20:08 +08:00
fbab3fc6d1
Only handle image mask if any option enabled
2023-04-14 17:24:55 -04:00
3af152d488
Fix image mask composite for weird resolutions
2023-04-14 17:17:14 -04:00
dab5002c59
sort self.word_embeddings without instantiating it a new dict
2023-04-13 23:19:10 -04:00
dff60e2e74
Update sd_models.py
2023-04-10 04:10:50 -05:00
a9902ca331
Update generation_parameters_copypaste.py
2023-04-10 04:03:01 -05:00
c510cfd24b
Update shared.py
...
fix typo
2023-04-10 03:43:56 -05:00
1c11062603
add token merging options to infotext when necessary. Bump tomesd
...
version
2023-04-10 03:41:05 -05:00
7c62bb2788
fix: support for default branch
2023-04-10 09:38:26 +08:00
c19618f370
fix(extras): fix batch image processing on 'Extras\Batch Process' tab
...
This change fixes an issue where an incorrect type was passed to the PIL.Image.open() function that caused the whole process to fail.
Scope of this change is limited to only batch image processing, and it shouldn't affect other functionality.
2023-04-09 21:33:09 +02:00
1aba8d82cb
feat: add branch support for extension installation
2023-04-09 22:22:43 +08:00
27b9ec60e4
sort embeddings by name (case insensitive)
2023-04-08 15:58:00 -04:00
d609f6030e
Add [batch_number] and [generation_number] filename patterns
2023-04-07 21:04:46 +09:00
63a6f9b4d9
Do not save init image by default
2023-04-07 12:13:51 +03:00
b3593d0997
Add support for saving init images in img2img
2023-04-06 19:42:26 +03:00
48c06af8dc
Pythonic way to achieve it
2023-04-05 20:51:29 -03:00
52a8f286ef
fix preprocess orientation
2023-04-05 20:28:00 -03:00
539a69860b
fix `--realesrgan-models-path` not working
2023-04-04 20:39:51 +08:00
3158d17ccf
fixed an issue with using ngrok for other connections and also ngrok not using auth_token
2023-04-04 07:41:55 +00:00
cf5a5773bf
:p
2023-04-04 02:39:13 -05:00
5c8e53d5e9
Allow different merge ratios to be used for each pass. Make toggle cmd flag work again. Remove ratio flag. Remove warning about controlnet being incompatible
2023-04-04 02:26:44 -05:00
2edf73b38f
Improved message clarity
2023-04-04 06:57:39 +00:00
5ebe3b2504
Added guard clause to prevent multiple tunnel creations
2023-04-04 06:50:29 +00:00
7201d940a4
Improve frontend responsiveness for some buttons
2023-04-03 21:27:48 -05:00
f7215906af
allow styles.csv to be symlinked or mounted in docker without moving the file around
2023-04-03 18:19:57 +02:00
fbaf6e4fd8
Namespace metadata fields
2023-04-02 21:41:23 -05:00
9a4e650800
Update postprocessing.py
...
Solution for anyone getting an error when batching on extras, even with a clean install of "stable diffusion webui"
2023-04-03 03:32:48 +02:00
7c016dd642
Calculate shorthash on merge if not exist
2023-04-02 19:06:39 -05:00
afc349c2c0
Add field for model merge type
...
Incase this is supported by other merge extensions
2023-04-02 18:40:33 -05:00
d132481058
Embed model merge metadata in .safetensors file
2023-04-02 17:41:55 -05:00
c707b7df95
remove excess condition
2023-04-01 23:47:10 -05:00
a609bd56b4
Transition to using settings through UI instead of cmd line args. Added feature to only apply to hr-fix. Install package using requirements_versions.txt
2023-04-01 22:18:35 -05:00
8c88bf4006
use pypi package for tomesd intead of manually cloning repo
2023-04-01 14:12:12 -05:00
26ab018253
delay import
2023-04-01 03:31:22 -05:00
ef8c044051
forgot to add reinstall arg back earlier since args moved out of shared
2023-04-01 03:21:23 -05:00
56680cd84a
first
2023-04-01 02:07:08 -05:00
18e4ca4694
Fix #9185
2023-03-31 10:54:42 +02:00
70ab21e67d
keep randomId simpler
2023-03-30 17:20:09 +08:00
90366b8d85
tool button
2023-03-30 17:20:09 +08:00
e0b58527ff
use condition to wait for result
2023-03-30 17:20:09 +08:00
4242e194e4
add a button to restore the current progress
2023-03-30 17:20:09 +08:00
9407f1731a
store the last generated result
2023-03-30 17:20:09 +08:00
dbca512154
add an internal API for obtaining current task id
2023-03-30 17:20:09 +08:00
44e8e9c368
fix live preview & alternate uncond guidance for better quality
2023-03-30 00:54:28 -04:00
3ccf6f5ae8
Add webui link
2023-03-29 19:26:52 -05:00
1c0544abdb
Add links for commits in table, if remote is from GitHub
2023-03-29 19:21:57 -05:00
64bbd3bf03
Make into divs
2023-03-29 19:00:51 -05:00
9b1fa82981
Add filename to UI and config name to filename
2023-03-29 18:55:57 -05:00
f3320b802c
Various UI fixes in config state tab
2023-03-29 18:35:25 -05:00
f22d0dde4e
Better checking of extension state from Git info
2023-03-29 18:32:29 -05:00
ad5afcaae0
Save/restore working webui/extension configs
2023-03-29 16:55:33 -05:00
67955ca9e5
Make selected tab configurable with UI config
2023-03-29 13:07:12 -05:00
22bcc7be42
attempted fix for infinite loading for settings that some people experience
2023-03-29 08:58:29 +03:00
70a0a11783
Changed behavior that puts the args from alwayson_script request in the script_args, so don't accidently resize the arg list if we get less arg then or default list has
2023-03-28 23:52:51 -04:00
bc90592031
increase range of negative guidance minimum sigma option
2023-03-28 20:59:31 -04:00
42082e8a32
performance increase
2023-03-28 20:56:01 -04:00
d667fc435f
add "resize by" and "resize to" tabs to img2img
2023-03-28 22:23:40 +03:00
3856ada5cc
do not add mask blur to infotext if there is no mask
2023-03-28 22:20:31 +03:00
433b3ab701
Revert "Merge pull request #7931 from space-nuko/img2img-enhance"
...
This reverts commit 42687593701b63afbedc
2023-03-28 20:36:57 +03:00
4268759370
Merge pull request #7931 from space-nuko/img2img-enhance
...
Add `Upscale by` and `Upscaler` options to img2img
2023-03-28 20:21:25 +03:00
1b63afbedc
sort hypernetworks and checkpoints by name
2023-03-28 20:03:57 +03:00
daa5a83bb7
Merge pull request #9052 from space-nuko/temp-disable-extensions
...
Temporary disable extensions option
2023-03-28 19:42:09 +03:00
f1db987e6a
Merge pull request #8958 from MrCheeze/variations-model
...
Add support for the unclip (Variations) models, unclip-h and unclip-l
2023-03-28 19:39:20 +03:00
4414d36bf6
Merge branch 'master' into img2img-enhance
2023-03-28 10:59:12 -04:00
082613036a
Merge branch 'master' into remove-watermark-option
2023-03-27 16:26:23 -05:00
fc8e1008ea
Make disable configurable between builtin/extra extensions
2023-03-27 12:44:49 -04:00
2a4d3d2124
Add temporary "disable all extensions" option for debugging use
2023-03-27 12:04:45 -04:00
77f9db3b08
serve css as independent files
2023-03-27 12:59:12 +03:00
9e82896d5f
remove an extra unneeded row in outputs
2023-03-27 10:20:01 +03:00
5fcd4bfa3d
do not read extensions' git stuff at startup
2023-03-27 10:02:30 +03:00
c7daba71de
Merge pull request #8669 from Vespinian/fix-api-running-unwanted_scripts
...
Fix for API running unwanted alwayson scripts
2023-03-27 08:11:34 +03:00
769def1e41
Merge pull request #8944 from SirFrags/extra_save_geninfo
...
Transfer generation parameters to previews
2023-03-27 08:06:54 +03:00
a70ae917ea
update button pressed down style for #8569
2023-03-27 08:05:55 +03:00
a7d6fc3b42
Merge pull request #8569 from missionfloyd/extra-networks-toggle
...
Make extra networks button togglable
2023-03-27 07:35:39 +03:00
c5e1efb4ca
Merge pull request #8525 from bluelovers/pr/sort-001
...
feat: try sort as ignore-case
2023-03-27 07:34:18 +03:00
3d09b4e99f
remove -y, bring back -f
2023-03-27 07:12:40 +03:00
ff0d97c1e3
bring back -y
2023-03-27 07:11:39 +03:00
8410b1351e
Merge branch 'AUTOMATIC1111:master' into extra-network-preview-lazyload
2023-03-26 21:50:22 -06:00
efac2cf1ab
Merge branch 'extra-network-preview-lazyload' of https://github.com/missionfloyd/stable-diffusion-webui into extra-network-preview-lazyload
2023-03-26 21:47:05 -06:00
3b5a3fab91
Merge pull request #8943 from space-nuko/fix-accordion-padding
...
Fix padding on accordion/dropdown list elements
2023-03-27 06:45:39 +03:00
1f08600345
overwrite xformers in the unclip model config if not available
2023-03-26 16:55:29 -04:00
4c1ad743e3
for img2img, use None as upscaler instead of erroring out if the desired upscaler is not found
2023-03-26 11:01:32 +03:00
8a34671fe9
Add support for the Variations models (unclip-h and unclip-l)
2023-03-25 21:03:07 -04:00
d64ff4248b
remove changes in textual_inversion.py
2023-03-26 06:15:09 +08:00
6f18c9b13f
Merge branch 'master' into extra-networks-toggle
2023-03-25 14:51:25 -06:00
c9647c8d23
Support Gradio's theme API
2023-03-25 16:11:41 -04:00
abc4d3a693
preview replace save params
2023-03-25 15:59:50 -04:00
d3b188c82d
Fix padding on accordion/dropdown list elements
2023-03-25 15:52:06 -04:00
c5f9f7c237
Use .success() callback on img2img preview inputs change
2023-03-25 14:26:36 -04:00
23f6dfce4c
Reworked this PR, now we have 2 default arg list (one for each tab) that will be initialized on the first api request and then reused afterwards. The init_script_args copies the corresponding default list and applies the modifications asked by the api request.
2023-03-25 14:16:35 -04:00
f371579571
Revert "Made copies of global scriptrunners, now we clear the copied scriptrunner of alwayson_scripts and only add back the ones that that were requested"
...
This reverts commit dfa258de5f
2023-03-25 14:11:46 -04:00
db602b100e
Revert "Comment fix"
...
This reverts commit f04bd037a5
2023-03-25 14:11:38 -04:00
7ea5d395c4
Add upscaler to img2img
2023-03-25 12:52:43 -04:00
68999d0b15
Add upscale slider to img2img
2023-03-25 12:52:35 -04:00
fb72066ef6
fixed button position
2023-03-25 23:03:22 +08:00
e3b9d0e3e8
Merge branch 'master' into img2img-detect-image-size
2023-03-25 23:00:45 +08:00
993c11549c
Merge branch 'AUTOMATIC1111:master' into master
2023-03-25 22:47:05 +08:00
b2fc7dba2e
Add option "keep original size" to textual inversion images preprocess
2023-03-25 22:45:41 +08:00
69eb2a9ee8
add missing extensions_dir, extensions_builtin_dir to extensions.py
2023-03-25 17:39:53 +03:00
9b2dcb04bc
Merge branch 'master' into master
2023-03-25 16:15:29 +03:00
8c801362b4
split commandline args into its own file
...
make launch.py use the same command line argument parser as the main program
2023-03-25 16:05:25 +03:00
3ec7e19f2b
Split history: mv temp modules/shared.py
2023-03-25 14:30:50 +03:00
a5cef4932f
Split history: mv modules/shared.py modules/cmd_args.py
2023-03-25 14:30:49 +03:00
6b00d876f7
Merge pull request #7936 from EllangoK/master
...
Custom height and width settings for Extra Networks cards
2023-03-25 13:01:49 +03:00
a03536f213
Merge pull request #8662 from vladmandic/api-handler
...
api error handler
2023-03-25 12:47:32 +03:00
616cc13b6b
update overflow-wrap: break-word; for gradio 3.23
2023-03-25 12:43:14 +03:00
63a2f8d822
Merge branch 'master' into master
2023-03-25 05:12:55 -04:00
8dbe793af5
Merge branch 'master' into extra-network-info
2023-03-25 12:08:24 +03:00
956ed9a737
Merge pull request #8780 from Brawlence/master
...
Unload and re-load checkpoint to VRAM on request (API & Manual)
2023-03-25 12:03:26 +03:00
8d2c582e3e
Merge pull request #8797 from ArrowM/master
...
Move `load_file_from_url` import
2023-03-25 11:34:07 +03:00
c0a7ff8055
Merge pull request #8803 from mlhub-action/fix_scripts_load_order
...
Fix scripts load order
2023-03-25 11:23:41 +03:00
90410e212f
Merge pull request #8814 from catboxanon/inpaint-mask
...
Add ability to display and/or save inpainting mask and masked composite
2023-03-25 11:21:45 +03:00
e8bbc344c3
Merge pull request #8824 from zimkjh/fix-variable-typo
...
fix variable typo
2023-03-25 11:04:46 +03:00
9d2551d593
Merge pull request #8647 from Tps-F/add_submodule
...
Support git submodule for extension and Fix Windows PermissionError
2023-03-25 11:02:41 +03:00
9ed04e759d
use HTTP request to fetch metadata for Lora cards instead of including it into the main page
2023-03-25 10:11:04 +03:00
724a63714d
Merge pull request #8878 from butaixianran/master
...
Fix None type error for TI module
2023-03-25 09:20:43 +03:00
89ea746f7c
Merge pull request #8866 from brkirch/mps-torch-2-0-nn-linear-workarounds
...
Add PyTorch 2.0 support for macOS, fix image generation on macOS 13.2.X
2023-03-25 09:17:09 +03:00
03c8eefbcc
Merge pull request #8782 from FNSpd/master
...
--upcast-sampling support for CUDA
2023-03-25 09:10:01 +03:00
4697def235
bump gradio to 3.23
...
fix broken image dragging
2023-03-25 09:00:37 +03:00
ff216820fd
fix extra networks ui
2023-03-25 09:00:37 +03:00
af2db25c84
enable queue by default
...
more stylistic changes
2023-03-25 09:00:37 +03:00
43a0912a07
hide delete button for single-item dropdown
...
more stylistic changes
2023-03-25 09:00:37 +03:00
9b2f205400
fix ctrl+up/down attention edit
...
fix dropdown obscured by live preview
stylistic changes
2023-03-25 09:00:36 +03:00
9f0da9f6ed
initial gradio 3.22 support
2023-03-25 09:00:36 +03:00
a9eab236d7
Update devices.py
2023-03-24 23:08:30 +04:00
803d44c474
Fix None type error for TI module
...
When user using model_name.png as a preview image, textural_inversion.py still treat it as an embeding, and didn't handle its error, just let python throw out an None type error like following:
```bash
File "D:\Work\Dev\AI\stable-diffusion-webui\modules\textual_inversion\textual_inversion.py", line 155, in load_from_file
name = data.get('name', name)
AttributeError: 'NoneType' object has no attribute 'get'
```
With just a simple `if data:` checking as following, there will be no error, breaks nothing, and now this module can works fine with user's preview images.
Old code:
```python
data = extract_image_data_embed(embed_image)
name = data.get('name', name)
```
New code:
```python
data = extract_image_data_embed(embed_image)
if data:
name = data.get('name', name)
else:
# if data is None, means this is not an embeding, just a preview image
return
```
Also, since there is no more errors on textual inversion module, from now on, extra network can set "model_name.png" as preview image for embedings.
2023-03-25 02:05:00 +08:00
280ed8f00f
Update sd_hijack_optimizations.py
2023-03-24 16:29:16 +04:00
beb7dda5d6
Update sd_hijack_unet.py
2023-03-24 16:25:42 +04:00
27fe3eb6a9
Add workaround for MPS layer_norm on PyTorch 2.0
...
On PyTorch 2.0, with MPS layer_norm only accepts float32 inputs. This was fixed shortly after 2.0 was finalized so the workaround can be applied with an exact version match.
2023-03-24 04:04:22 -04:00
c5142e2fbe
Add workaround for broken nn.Linear on macOS 13.2
...
Credit to danieldk (https://github.com/explosion/curated-transformers/pull/124 ) for the workaround this is based on.
2023-03-24 04:04:20 -04:00
771ea212de
added button to grab the width and height from the loaded image in img2img
2023-03-24 12:41:17 +08:00
d86beb8228
Remove "do not add watermark to images" option
2023-03-23 17:09:59 -04:00
252f15e046
added search textbox to filter available extensions
2023-03-23 23:43:00 +08:00
92e173d414
fix variable typo
2023-03-23 14:28:08 +09:00
caf84e8233
Expose inpainting mask and composite
...
For inpainting, this exposes the mask and masked composite and gives
the user the ability to display these in the web UI,
save to disk, or both.
2023-03-22 17:51:40 +00:00
cd3cd0fca0
Fix scripts load order
...
- 1st webui, 2nd extensions-builtin, 3rd extensions
- to load scripts independent of --data-dir
- change load order key [x.basedir, x.filename, x.path] to [orderby(x.basedir), x.filename, x.path]
e.g., scripts/xyz_grid.py dependent extentions should loaded later
extensions\sd-webui-controlnet\scripts\xyz_grid_support.py
extensions\sd-webui-additional-networks\scripts\xyz_grid_support.py
2023-03-23 01:28:09 +09:00
64b7e83823
Fix scripts load order
...
- 1st webui, 2nd extensions-builtin, 3rd extensions
- to load scripts independent of --data-dir
- change load order key [x.basedir, x.filename, x.path] to [orderby(x.basedir), x.filename, x.path]
e.g., scripts/xyz_grid.py dependent extentions should loaded later
extensions\sd-webui-controlnet\scripts\xyz_grid_support.py
extensions\sd-webui-additional-networks\scripts\xyz_grid_support.py
2023-03-22 18:24:11 +09:00
00bd271faf
Move `load_file_from_url`
...
Why?
one of the internal calls of `load_file_from_url` import cv2, which locks the cv2 site-package, which extensions may (and in our case, is) breaking the installation of some libraries. The base project should be limiting its import of unnecessary libraries when possible during the installation phase.
2023-03-21 21:13:30 -05:00
1d096ed145
Lazy load extra network images
2023-03-21 16:07:24 -06:00
a80d7d090c
Update script_callbacks.py
2023-03-21 18:47:05 +01:00
c84c9df737
Update sd_hijack_optimizations.py
2023-03-21 14:50:22 +04:00
91cfa9718c
Update sd_hijack_unet.py
2023-03-21 14:47:43 +04:00
254d994643
Update devices.py
2023-03-21 14:45:39 +04:00
4cbbb881ee
Unload checkpoints on Request
...
…to free VRAM.
New Action buttons in the settings to manually free and reload checkpoints, essentially
juggling models between RAM and VRAM.
2023-03-21 09:28:50 +03:00
8e3ced73a8
Add event.stopPropagation() to extraNetworksShowMetadata()
...
Prevent bubbling the same way "replace preview" does
2023-03-20 18:04:22 -06:00
64fc936738
Don't bubble when metadata_button is clicked
2023-03-19 19:30:28 -06:00
147d2922ff
Cross device link
2023-03-16 12:35:48 +09:00
f04bd037a5
Comment fix
2023-03-15 22:27:54 -04:00
dfa258de5f
Made copies of global scriptrunners, now we clear the copied scriptrunner of alwayson_scripts and only add back the ones that that were requested
2023-03-15 22:17:32 -04:00
5387576c59
api error handler
2023-03-15 15:11:04 -04:00
79ed567b12
remove unused library
...
I'm sorry I forgot.
2023-03-15 22:42:53 +09:00
4845db4e32
Update ui_extensions.py
...
Add git submodule and Fix WinError
2023-03-15 20:29:50 +09:00
fd672a79af
fix: remove cmp
...
by ChatGPT
2023-03-15 13:17:09 +08:00
f5e4436453
Merge branch 'master' into improved-hr-conflict-test
2023-03-14 16:55:59 +03:00
a9fed7c364
Merge pull request #8503 from mcmonkey4eva/filename-length-limit-fix
...
Add correction file filename length limits on *nix systems
2023-03-14 11:28:13 +03:00
6a04a7f20f
fix an error loading Lora with empty values in metadata
2023-03-14 11:22:29 +03:00
8b35b64e11
Merge pull request #8589 from vladmandic/unipc
...
add progressbar to unipc sampler
2023-03-14 11:19:21 +03:00
f9b0465c8b
Merge pull request #8588 from hananbeer/fix/undefined_extra_network_data
...
initialize extra_network_data before use
2023-03-14 11:18:30 +03:00
4281432594
Update ui_extra_networks.py
...
I updated it so that no error message is displayed when setting a webp for the preview image.
2023-03-14 15:36:08 +09:00
c19530f1a5
Add view metadata button for Lora cards.
2023-03-14 09:10:26 +03:00
03a80f198e
add pbar to unipc
2023-03-13 12:35:30 -04:00
4d26c7da57
initialize extra_network_data before use
2023-03-13 17:37:29 +02:00
9e23bacfbc
Make extra networks button togglable
2023-03-12 17:07:03 -06:00
af9158a8c7
update `fullfn` properly
2023-03-12 12:36:04 -07:00
48df6d66ea
add safety check in case of short extensions
...
so eg if a two-letter or empty extension is used, `.txt` would break, this `max` call protects that.
2023-03-12 12:33:29 -07:00
a71b7b5ec0
relocate filename length limit to better spot
2023-03-12 12:30:31 -07:00
dfeee786f9
display correct timings after restarting UI
2023-03-12 21:25:22 +03:00
a00cd8b9c1
attempt to fix memory monitor with multiple CUDA devices
2023-03-12 21:04:17 +03:00
27eedb6966
change extension index link to the new dedicated repo instead of wiki
2023-03-12 17:20:17 +03:00
bd67c41f54
force refresh tqdm before close
2023-03-12 09:19:23 -04:00
adf723a9b2
Merge pull request #8492 from zhanghua000/absolute-path
...
fix: gradio's ValueError about fetching extensions files
2023-03-12 08:55:15 +03:00
6106f6d0a0
Merge pull request #7965 from Kilvoctu/extranet-buttons
...
Use emojis for extra network buttons
2023-03-12 08:25:03 +03:00
beb96bd115
Merge pull request #8515 from EllangoK/unipc-typo
...
Fix dims typo in unipc
2023-03-12 08:24:17 +03:00
bbc4b0478a
Merge pull request #8518 from brkirch/remove-bool-test
...
Fix image generation on macOS 13.3 betas
2023-03-12 08:14:26 +03:00
0492424121
feat: try sort as ignore-case
...
https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/8368
2023-03-12 10:18:33 +08:00
a4cb96d4ae
Remove test, use bool tensor fix by default
...
The test isn't working correctly on macOS 13.3 and the bool tensor fix for cumsum is currently always needed anyway, so enable the fix by default.
2023-03-11 17:35:17 -05:00
48f4abd2e6
fix dims typo in unipc
2023-03-11 15:52:14 -05:00
64efb3d9e0
Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webui
2023-03-11 14:35:20 -05:00
49bbdbe447
small diff whitespace cleanup
2023-03-11 14:34:56 -05:00
247a34498b
restore text, remove 'close'
...
don't use emojis for extra network buttons; remove 'close'
2023-03-11 13:11:26 -06:00
27e319dc4f
alternative solution for #8089
2023-03-11 21:22:52 +03:00
5546e71a10
Fixed whitespace
2023-03-11 12:35:20 -05:00
46f9fe3cd6
Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webui
2023-03-11 12:33:35 -05:00
2174f58dae
Changed alwayson_script_name and alwayson_script_args api params to 1 alwayson_scripts param dict
2023-03-11 12:21:33 -05:00
7fd19fa4e7
initial fix for filename length limits on *nix systems
2023-03-11 07:22:22 -08:00
e0ca78509a
Merge pull request #8118 from adam-huganir/8116-gitpython-api-breaking-change
...
git 3.1.30 api change, issue #8116
2023-03-11 17:47:51 +03:00
d3dd6cc01c
Merge pull request #8175 from vladmandic/image_size
...
adds checks for resulting image size to avoid memory issues
2023-03-11 16:45:35 +03:00
76bc72116e
Merge pull request #7818 from space-nuko/extension-paste-field-names
...
Allow extensions to declare paste fields for "Send to X" buttons
2023-03-11 16:44:20 +03:00
b9fd9c81de
Merge pull request #7963 from xSinStarx/patch-1
...
Bug Fix: Fixes img2img Negative Token Counter
2023-03-11 16:34:34 +03:00
f968270fec
Merge pull request #7812 from vladmandic/hide_ui_tabs
...
allow configurable hiding of ui tabs
2023-03-11 16:00:43 +03:00
6da2027213
save previews for extra networks in the selected format
2023-03-11 15:46:20 +03:00
9320139bd8
support three extensions for preview instead of one: png, jpg, webp
2023-03-11 15:33:24 +03:00
ce68ab8d0d
remove underscores from function names in #8366
...
remove LRU from #8366 because I don't know why it's there
2023-03-11 15:27:42 +03:00
c239b3d7a8
Merge pull request #8366 from akx/extra-net-descs
...
Extra network description files
2023-03-11 15:20:34 +03:00
e15c4f31e3
Merge pull request #8042 from fkunn1326/master
...
Add .mjs support for extensions
2023-03-11 15:18:05 +03:00
8e0d16e746
modules/sd_vae_approx.py: fix VAE-approx path
2023-03-11 20:00:12 +08:00
8106117a47
models/ui.py: make the path of script.js absolute
2023-03-11 20:00:11 +08:00
98695c1885
Merge pull request #8050 from Tpinion/master
...
Bugfix: Filter out temporary files that will be generated if the download fails.
2023-03-11 14:58:45 +03:00
7f2005127f
rename CFGDenoiserParams fields for #8064
2023-03-11 14:52:29 +03:00
af416a2dbd
Merge pull request #8064 from laksjdjf/master
...
Add cond and uncond hidden states to CFGDenoiserParams
2023-03-11 14:48:55 +03:00
45905b92a9
Merge pull request #8100 from missionfloyd/webp-lossless
...
Add lossless webp option
2023-03-11 14:35:53 +03:00
da3f942ab2
Merge pull request #8017 from space-nuko/before-process-batch
...
Add `before_process_batch` script callback
2023-03-11 14:33:38 +03:00
aaa367e35c
new setting: Extra text to add before <...> when adding extra network to prompt
2023-03-11 14:18:18 +03:00
6705b1764a
Merge pull request #8092 from infinitewarp/sort-upscalers
...
sort upscalers by name
2023-03-11 13:44:41 +03:00
8ec0442dcd
Merge pull request #8322 from yeataro/master
...
add: /sdapi/v1/scripts in API
2023-03-11 13:43:34 +03:00
3531a50080
rename fields for API for saving/sending images
...
save images to correct directories
2023-03-11 13:22:59 +03:00
bb3ecc3285
Merge pull request #8287 from vladmandic/save-images
...
Allow saving of images generated via API
2023-03-11 13:03:23 +03:00
d81c503918
Merge pull request #8367 from pamparamm/scaled-dot-product-attention
...
Add scaled dot product attention
2023-03-11 12:24:03 +03:00
58b5b7c2f1
add UniPC options to infotext
2023-03-11 12:09:36 +03:00
f261a4a53c
use selected device instead of always cuda for UniPC sampler
2023-03-11 11:56:05 +03:00
5fef67f6ee
Requested changes
2023-03-10 19:56:14 -05:00
ac38ad7e60
Merge remote-tracking branch 'origin/master' into unipc
2023-03-10 19:42:46 -05:00
8d7fa2f67c
sdp_attnblock_forward hijack
2023-03-10 22:48:41 +05:00
f6e2737840
Negative prompt fix
2023-03-10 12:13:55 +00:00
0981dea948
sdp refactoring
2023-03-10 12:58:10 +05:00
37acba2633
argument to disable memory efficient for sdp
2023-03-10 12:19:36 +05:00
f85a192f99
Update modules/api/api.py
...
Suggested change by @akx
Co-authored-by: Aarni Koskela <akx@iki.fi>
2023-03-07 04:04:35 +08:00
fec0a89511
scaled dot product attention
2023-03-07 00:33:13 +05:00
06f167da37
Extra networks: support .txt description sidecar file
2023-03-06 21:15:33 +02:00
49b1dc5e07
Deduplicate extra network preview-search code
2023-03-06 21:00:34 +02:00
d118cb6ea3
use lowercase name for sorting; keep `UpscalerLanczos` and `UpscalerNearest` at the start of the list with `UpscalerNone`
...
Co-authored-by: catboxanon <122327233+catboxanon@users.noreply.github.com>
2023-03-06 13:21:42 -05:00
b012d70f15
update using original defaults
2023-03-04 17:51:37 -05:00
b9fdb9f701
Fix crash when hr is disabled
2023-03-04 18:09:05 +00:00
c48bbccf12
add: /sdapi/v1/scripts in API
...
API for get scripts list
2023-03-04 11:46:07 +08:00
e97b83bdbb
Merge branch 'master' into improved-hr-conflict-test
2023-03-03 19:49:24 +03:00
51f81efb02
Image processing changes
...
Image processing changes
2023-03-03 19:45:33 +03:00
f8e219bad9
allow api requests to specify do not send images in response
2023-03-03 09:00:52 -05:00
23d4fb5bf2
allow saving of images via api
2023-03-03 08:29:10 -05:00
c6c2a59333
comment clarification
2023-02-27 23:45:59 -05:00
a39c4cf766
small refactor of api.py
2023-02-27 23:27:33 -05:00
3b6de96467
Added alwayson_script_name and alwayson_script_args to api
...
Added 2 additional possible entries in the api request: alwayson_script_name, a string list, and, alwayson_script_args, a list of list containing the args of each script. This allows us to send args to always on script and keep backwards compatibility with old script_name and script_arg api params
2023-02-27 21:51:20 -05:00
3c6459154f
add check for resulting image size
2023-02-27 17:28:04 -05:00
6d92d95a33
git 3.1.30 api change
2023-02-25 19:15:06 +00:00
aa108bd02a
Add lossless webp option
2023-02-24 20:57:18 -07:00
b15bc73c99
sort upscalers by name
2023-02-24 14:45:08 -05:00
534cf60afb
Update script_callbacks.py
2023-02-24 14:26:55 +09:00
9a1435946c
Update sd_samplers_kdiffusion.py
2023-02-24 14:04:23 +09:00
327186b484
Update script_callbacks.py
2023-02-24 14:03:46 +09:00
ac4c7f05cd
Filter out temporary files that will be generated if the download fails.
2023-02-24 00:42:29 +08:00
b90cad7f31
Add .mjs support for extensions
2023-02-23 03:29:22 +00:00
a2d635ad13
Add before_process_batch script callback
2023-02-22 01:52:53 -08:00
32a4c8d961
use emojis for extra network buttons
...
🔄 for refresh
❌ for close
2023-02-20 15:14:06 -06:00
b0f2653541
Fixes img2img Negative Token Counter
...
The img2img negative token counter is counting the txt2img negative prompt.
2023-02-20 12:39:38 -08:00
f71a3c9c3a
convert resolution to int using round()
2023-02-20 17:47:20 +09:00
ca2b8faa83
custom height, width settings for extra networks
2023-02-19 14:38:22 -05:00
83829471de
make ui as multiselect instead of string list
2023-02-19 09:21:44 -05:00
8affa42588
Merge branch 'AUTOMATIC1111:master' into hide_ui_tabs
2023-02-19 09:19:25 -05:00
014e7323f6
when exists
2023-02-19 20:49:07 +09:00
c77f01ff31
fix auto sd download issue
2023-02-19 20:37:40 +09:00
c3d5a6ed37
Merge pull request #7300 from Ju1-js/master
...
Gradio Auth - Read from External File
2023-02-19 13:02:05 +03:00
11183b4d90
fix for #6700
2023-02-19 12:44:56 +03:00
dfb3b8f398
Merge branch 'master' into weighted-learning
2023-02-19 12:41:29 +03:00
4313777322
Merge pull request #7703 from minux302/hotfix/fix_hn_api_arg
...
fix arg for train_hypernetwork api
2023-02-19 12:36:01 +03:00
09835363ab
Merge pull request #7572 from CurtisDS/fix-id-handle-in-extra-networks
...
Update ui_extra_networks.py to fix div id's that have spaces in them
2023-02-19 12:26:11 +03:00
b908bed883
remove unneeded return from #7583
2023-02-19 12:23:40 +03:00
563724f6e9
Merge pull request #7583 from EllangoK/master
...
Calls modules.sd_vae.refresh_vae_list(), fixes VAE list not updating
2023-02-19 12:23:06 +03:00
b63a13c5ed
Merge pull request #7651 from vladmandic/missing-imports
...
Add missing imports
2023-02-19 12:16:58 +03:00
e287d9b294
Merge pull request #7650 from vladmandic/img2img-fix
...
Convert image from RGBA to RGB before saving
2023-02-19 12:15:27 +03:00
fe46a08f52
add slash to non-empty dirs in extra networks interface
2023-02-19 12:09:25 +03:00
226bc04653
Merge pull request #7637 from brkirch/fix-hypernetworks-pix2pix
...
Fix hypernetworks and instruct pix2pix not working with `--upcast-sampling`
2023-02-19 11:15:41 +03:00
3fcc087317
Merge pull request #7731 from opparco/master
...
Add cfg_denoised_callback
2023-02-19 11:09:47 +03:00
fd4ac5187a
Revert "Aspect ratio sliders"
2023-02-19 10:55:39 +03:00
b20f28eea9
Merge pull request #7601 from Gerschel/aspect_ratio_sliders
...
Aspect ratio sliders
2023-02-19 10:53:18 +03:00
9c4eaac61f
Merge pull request #7691 from missionfloyd/16bit-convert
...
Convert 16-bit greyscale to 8-bit when saving as JPEG
2023-02-19 10:15:49 +03:00
2a4f893570
Merge pull request #7727 from missionfloyd/face-restore-setting
...
Fix face restorers setting
2023-02-19 10:14:42 +03:00
fb2354cb2a
reword settings for 4chan export, remove unneded try/excepts, add try/except for actually saving JPG
2023-02-19 10:12:45 +03:00
e572c3ed38
Merge pull request #7564 from w-e-w/configurable_image_downscale
...
Configurable JPG downscale threshold
2023-02-19 10:01:42 +03:00
1646991637
display 8 (rather than 7) characters of the extension commit hash in the installed extensions table
2023-02-19 09:54:04 +03:00
d023532c55
Merge pull request #7798 from vladmandic/extensions
...
add version to extensions table
2023-02-19 09:52:19 +03:00
15f4b217b1
fix the a merge conflict resolve i did that entirely breaks image generation
2023-02-19 09:50:14 +03:00
a77ac2eeaa
Merge pull request #7730 from CCRcmcpe/fix-dpm-sde-batch
...
Fix DPM++ SDE not deterministic across different batch sizes (#5210 )
2023-02-19 09:38:15 +03:00
a742facd95
make PNG info tab work properly with parameter overrides
2023-02-19 09:30:57 +03:00
6911deb242
Merge branch 'master' into fix-save-params-2
2023-02-19 09:15:45 +03:00
c69494673d
Merge pull request #7824 from missionfloyd/download-model
...
Download model if none are found
2023-02-19 09:00:48 +03:00
b66b6829aa
Merge pull request #7789 from space-nuko/extra-networks-per-batch
...
Apply extra networks per-batch instead of per-session (fixes wildcards)
2023-02-19 08:44:40 +03:00
b5f69ad6af
simply long version display for torch in UI
2023-02-19 08:38:38 +03:00
9c7e6d5bba
store and print real torch version
2023-02-18 11:31:02 -05:00
b20737815a
Fix params.txt saving for infotexts modified by process_batch
2023-02-16 21:44:46 -08:00
c4ea16a03f
Add ".vae.ckpt" to ext_blacklist
2023-02-15 19:47:30 -07:00
edb10092de
Add ability to choose using weighted loss or not
2023-02-15 10:03:59 +01:00
bc50936745
Call weighted_forward during training
2023-02-15 10:03:59 +01:00
21642000b3
Add PNG alpha channel as weight maps to data entries
2023-02-15 10:03:59 +01:00
c4bfd20f31
Hijack to add weighted_forward to model: return loss * weight map
2023-02-15 10:03:59 +01:00
f55a7e04d8
Fix error when batch count > 1
2023-02-15 16:57:18 +08:00
1615f786ee
Download model if none are found
2023-02-14 20:54:02 -07:00
7df7e4d227
Allow extensions to declare paste fields for "Send to X" buttons
2023-02-14 03:55:42 -08:00
a320d157ec
all hiding of ui tabs
2023-02-13 20:26:47 -05:00
7893533674
add version to extensions table
2023-02-13 11:04:34 -05:00
0a4917ac40
Apply extra networks per-batch instead of per-session (fixes wildcards)
2023-02-13 03:33:28 -08:00
716a69237c
support SD2.X models
2023-02-11 06:18:34 -08:00
b78c5e87ba
Add cfg_denoised_callback
2023-02-11 11:18:38 +09:00
9e27af76d1
Fix DPM++ SDE not deterministic across different batch sizes ( #5210 )
2023-02-11 10:12:16 +08:00
fb274229b2
bug fix
2023-02-10 14:30:35 -08:00
bf9b1d64a3
Fix face restorers setting
2023-02-10 15:27:08 -07:00
06cb0dc920
Fix UniPC order
2023-02-10 05:36:41 -08:00
79ffb9453f
Add UniPC sampler settings
2023-02-10 05:27:05 -08:00
c88dcc20d4
UniPC does not support img2img (for now)
2023-02-10 05:00:54 -08:00
21880eb9e5
Fix logspam and live previews
2023-02-10 04:47:08 -08:00
1253199889
Working UniPC (for batch size 1)
2023-02-10 03:30:20 -08:00
33947a3c66
fix arg for hypernetwork train api
2023-02-10 17:58:35 +09:00
73a97cac11
Use RGB for webp
...
Doesn't support greyscale (L)
2023-02-09 17:04:55 -07:00
463ab84180
Convert 16-bit greyscale to 8-bit when saving as JPEG
2023-02-09 02:13:49 -07:00
374fe636b8
Squashed commit of the following:
...
commit b030b67ad005bfe29bcda692238a00042dcae816
Author: Gerschel <Gerschel_Payne@hotmail.com>
Date: Wed Feb 8 16:38:56 2023 -0800
styling adjustements
commit 80a2acb0230dd77489b0eb466f2efe827a053f6d
Author: Gerschel <Gerschel_Payne@hotmail.com>
Date: Wed Feb 8 10:49:47 2023 -0800
badge indicator toggles visibility by selection
commit 898922e025a6422ac947fb45c1fa4f1109882f0a
Merge: 745382a0 31bbfa72
Author: Gerschel <9631031+Gerschel@users.noreply.github.com>
Date: Wed Feb 8 08:35:26 2023 -0800
Merge pull request #1 from w-e-w/Rounding-Method
Rounding Method
commit 31bbfa729a15ef35fa1f905345d3ba2b17b26ab9
Author: w-e-w <40751091+w-e-w@users.noreply.github.com>
Date: Wed Feb 8 19:41:45 2023 +0900
use switch
commit 85dbe511c33521d3ac62224bf0e0f3a48194ce63
Author: w-e-w <40751091+w-e-w@users.noreply.github.com>
Date: Wed Feb 8 16:47:52 2023 +0900
Rounding Method
commit 745382a0f4b8d16241545a3460d5206915959255
Author: Gerschel <Gerschel_Payne@hotmail.com>
Date: Tue Feb 7 21:19:20 2023 -0800
default set to round
commit 728579c618af30ec98a5af0991bd3f28bdaca399
Author: Gerschel <Gerschel_Payne@hotmail.com>
Date: Tue Feb 7 21:17:03 2023 -0800
cleaned some commented code out; added indicator
commit 5b288c24a1edd8a5c2f35214b9634316d05b8dae
Author: Gerschel <Gerschel_Payne@hotmail.com>
Date: Tue Feb 7 18:19:00 2023 -0800
needs cleaning; attempt at rounding
commit d9f18ae92b929576b0b8c5f1ef8b3b38e441e381
Author: Gerschel <Gerschel_Payne@hotmail.com>
Date: Tue Feb 7 15:46:25 2023 -0800
add rounding option in setting for aspect ratio
commit af22106802c9e42205649e4c71c23fcf5b8c62f6
Author: Gerschel <Gerschel_Payne@hotmail.com>
Date: Tue Feb 7 13:18:45 2023 -0800
added some ratios, sorted ratios by commonality
commit 11e2fba73cffe8cdbf4cd0860641b94428ca0e74
Author: Gerschel <Gerschel_Payne@hotmail.com>
Date: Tue Feb 7 10:46:53 2023 -0800
snaps to mulitples of 8 and along ratio
commit fa00387e07460b10ee82671a1bfa8687e00ee60b
Author: Gerschel <Gerschel_Payne@hotmail.com>
Date: Mon Feb 6 14:54:59 2023 -0800
updated slidercomponentcontroller
commit 8059bc111c3e2d1edb3314e05ab21b65120fa1dd
Author: Gerschel <Gerschel_Payne@hotmail.com>
Date: Mon Feb 6 14:29:11 2023 -0800
added step size adjustment on number field
commit 641157b9f27a874a24ee7b0a854a092e9eac3eec
Author: Gerschel <Gerschel_Payne@hotmail.com>
Date: Mon Feb 6 14:12:03 2023 -0800
added return step size to default when ratio is disabled
commit 5fb75ad28f2476f36100ec93922a8199adbd2a68
Author: Gerschel <Gerschel_Payne@hotmail.com>
Date: Mon Feb 6 14:09:34 2023 -0800
added step size adjustment
commit e33532883bc4709cd41c3775cbb646d1d5ab0584
Author: Gerschel <Gerschel_Payne@hotmail.com>
Date: Mon Feb 6 11:56:15 2023 -0800
adjusted dropdown size, padding, text-align
commit 81937329cee77f466c5a5b23c268d0c810128f84
Author: Gerschel <Gerschel_Payne@hotmail.com>
Date: Mon Feb 6 11:39:57 2023 -0800
added positioning and styling
commit 86eb4583782d92880a9a113a54ffbac9d92f3753
Author: Gerschel <Gerschel_Payne@hotmail.com>
Date: Mon Feb 6 08:54:45 2023 -0800
fix typo in defaults; added preventDefault in event
2023-02-08 18:57:32 -08:00
3ca41dbded
add missing import
...
used later in line 70
2023-02-08 07:10:13 -05:00
3ee9ca5cb0
add missing import
...
used later in line 418
2023-02-08 07:08:09 -05:00
4c562a9832
convert rgba to rgb
...
some image format (e.g. jpg) do not support rgba
2023-02-08 07:03:36 -05:00
2016733814
Apply hijacks in ddpm_edit for upcast sampling
...
To avoid import errors, ddpm_edit hijacks are done after an instruct pix2pix model is loaded.
2023-02-07 22:53:45 -05:00
4738486d8f
Support for hypernetworks with --upcast-sampling
2023-02-06 18:10:55 -05:00
5d483bf307
aspect ratio for dim's; sliders adjust by ratio
...
Default choices added to settings in user interface section
Choices are editable by user
User selects from dropdown.
When you move one slider, the other adjusts according to the ratio
chosen.
Vice versa for the other slider.
Number fields for changes work as well.
For disabling ratio, an unlock pad "🔓 " is available as a default.
This string can be changed to anything to serve as a disable,
as long as there is no colon ":".
Ratios are entered in this format, floats or ints with a colon "1:1".
The string is split at the colon, parses left and right as floats to
perform the math.
2023-02-06 08:18:04 -08:00
9a22c63f47
call modules.sd_vae.refresh_vae_list()
2023-02-06 00:52:31 -05:00
584f782391
Update ui_extra_networks.py
...
update the string used to build the ID handle to replace spaces with underscore
2023-02-05 16:42:45 -05:00
c3bd113a0b
Image info fix
2023-02-05 15:24:41 +00:00
f4b78e73a4
Merge branch 'AUTOMATIC1111:master' into improved-hr-conflict-test
2023-02-05 18:02:44 +03:00
fe33be6cac
use Default if ValueError
2023-02-05 23:33:05 +09:00
6d11cda418
configurable image downscale
...
allowing the user to configure the image downscale parameters in setting
2023-02-05 23:12:42 +09:00
0ca1a64cfc
adds grid margins to xyz plot and prompt matrix
2023-02-05 03:44:56 -05:00
3993aa43e9
Merge pull request #7535 from mcmonkey4eva/fix-symlink-extra-network
...
fix symlinks in extra networks ui
2023-02-05 11:28:30 +03:00
27a50d4b38
Merge pull request #7554 from techneconn/feature/prompt_hash_option
...
Add prompt_hash option for file/dir name pattern
2023-02-05 11:27:05 +03:00
475095f50a
Merge pull request #7528 from spezialspezial/patch-1
...
Catch broken model symlinks early | Quickfix modelloader.py
2023-02-05 11:24:32 +03:00
668d7e9b9a
make it possible to load SD1 checkpoints without CLIP
2023-02-05 11:21:00 +03:00
5a1b62e9f8
Add prompt_hash option for file/dir name pattern
2023-02-05 15:48:51 +09:00
88a46e8427
fix symlinks in extra networks ui
...
'absolute' and 'resolve' are equivalent, but 'resolve' resolves symlinks (which is an obscure specialty behavior usually not wanted) whereas 'absolute' treats symlinks as folders (which is the expected behavior). This commit allows you to symlink folders within your models/embeddings/etc. dirs and have preview images load as expected without issue.
2023-02-04 09:10:00 -08:00
6524478850
Update modelloader.py
...
os.path.getmtime(filename) throws exception later in codepath when meeting broken symlink. For now catch it here early but more checks could be added for robustness.
2023-02-04 16:52:15 +01:00
3e0f9a7543
fix issue with switching back to checkpoint that had its checksum calculated during runtime mentioned in #7506
2023-02-04 15:23:16 +03:00
40e51fd6ef
add margin parameter to draw_grid_annotations
2023-02-04 13:29:04 +03:00
21593c8082
Merge pull request #7466 from ctwrs/master
...
Add .jpg to allowed thumb formats
2023-02-04 12:07:45 +03:00
c0e0b5844d
Merge pull request #7470 from cbrownstein-lambda/update-error-message-no-checkpoint
...
Update error message WRT missing checkpoint file
2023-02-04 12:07:12 +03:00
81823407d9
add --no-hashing
2023-02-04 11:38:56 +03:00
30228c67ca
Merge pull request #7461 from brkirch/mac-fixes
...
Move Mac related code to separate file
2023-02-04 11:22:52 +03:00
c4b9ed1a27
make Image CFG Scale only show if instrutpix2pix model is loaded
2023-02-04 11:18:44 +03:00
72dd5785d9
merge CFGDenoiserEdit and CFGDenoiser into single object
2023-02-04 11:06:17 +03:00
4306659c4d
Remove unused code
2023-02-04 01:22:06 -05:00
ba6a4e7e94
Use original CFGDenoiser if image_cfg_scale = 1
...
If image_cfg_scale is =1 then the original image is not used for the output. We can then use the original CFGDenoiser to get the same result to support AND functionality.
Maybe in the future AND can be supported with "Image CFG Scale"
2023-02-03 19:46:13 -05:00
c27c0de0f7
txt2img Hires Fix
2023-02-03 19:15:32 -05:00
6c6c6636bb
Image CFG Added (Full Implementation)
...
Uses separate denoiser for edit (instruct-pix2pix) models
No impact to txt2img or regular img2img
"Image CFG Scale" will only apply to instruct-pix2pix models and metadata will only be added if using such model
2023-02-03 18:19:56 -05:00
3b2ad20ac1
Processing only, no CFGDenoiser change
...
Allows instruct-pix2pix
2023-02-02 19:19:45 -05:00
cf0cfefe91
Revert "instruct-pix2pix support"
...
This reverts commit 269833067d
2023-02-02 19:15:38 -05:00
5ca4230524
Merge branch 'master' of https://github.com/Rucadi/stable-diffusion-webui-polling
2023-02-02 20:12:08 +01:00
eb5eb8aa11
Add a callback called before reloading the server
2023-02-02 20:10:47 +01:00
3662a274e2
Add polling callback
2023-02-02 20:10:47 +01:00
269833067d
instruct-pix2pix support
2023-02-02 09:37:01 -05:00
fb97acef63
Update error message WRT missing checkpoint file
...
The Safetensors format is also supported.
2023-02-01 14:51:06 -08:00
92bae77b88
Add .jpg to allowed thumb formats
2023-02-01 22:28:39 +01:00
1b8af15f13
Refactor Mac specific code to a separate file
...
Move most Mac related code to a separate file, don't even load it unless web UI is run under macOS.
2023-02-01 14:05:56 -05:00
07edf57409
Merge pull request #7357 from EllangoK/btn-fix
...
Fixes switch height/width btn unbound error
2023-02-01 16:29:58 +03:00
30a64504b1
Merge pull request #7414 from joecodecreations/master
...
Changes use_original_name_batch to default to True
2023-02-01 16:22:16 +03:00
2217331cd1
Refactor MPS fixes to CondFunc
2023-02-01 06:36:22 -05:00
7738c057ce
MPS fix is still needed :(
...
Apparently I did not test with large enough images to trigger the bug with torch.narrow on MPS
2023-02-01 05:23:58 -05:00
0426b34789
Adding default true to use_original_name_batch as images should by default hold the same name to help keep sequenced images in their correct order
2023-01-30 21:46:52 -05:00
3ec2eb8bf1
Merge branch 'master' into improved-hr-conflict-test
2023-01-30 15:35:13 +03:00
ee9fdf7f62
Add --skip-version-check to disable messages asking users to upgrade torch.
2023-01-30 14:56:28 +03:00
ab059b6e48
make the program read Discard penultimate sigma from generation parameters
2023-01-30 10:52:15 +03:00
040ec7a80e
make the program read Eta and Eta DDIM from generation parameters
2023-01-30 10:47:09 +03:00
4df63d2d19
split samplers into one more files for k-diffusion
2023-01-30 10:11:30 +03:00
274474105a
Split history sd_samplers.py to sd_samplers_kdiffusion.py
2023-01-30 09:51:23 +03:00
95916e3777
Split history sd_samplers.py to sd_samplers_kdiffusion.py
2023-01-30 09:51:23 +03:00
2db8ed32cd
Split history sd_samplers.py to sd_samplers_kdiffusion.py
2023-01-30 09:51:23 +03:00
f4d0538bf2
Split history sd_samplers.py to sd_samplers_kdiffusion.py
2023-01-30 09:51:23 +03:00
aa54a9d416
split compvis sampler and shared sampler stuff into their own files
2023-01-30 09:51:06 +03:00
f8fcad502e
Split history sd_samplers.py to sd_samplers_common.py
2023-01-30 09:37:51 +03:00
58ae93b954
Split history sd_samplers.py to sd_samplers_common.py
2023-01-30 09:37:50 +03:00
6e78f6a896
Split history sd_samplers.py to sd_samplers_common.py
2023-01-30 09:37:50 +03:00
5feae71dd2
Split history sd_samplers.py to sd_samplers_common.py
2023-01-30 09:37:50 +03:00
449531a6c5
Split history sd_samplers.py to sd_samplers_compvis.py
2023-01-30 09:35:53 +03:00
9b8ed7f8ec
Split history sd_samplers.py to sd_samplers_compvis.py
2023-01-30 09:35:53 +03:00
9118b08606
Split history sd_samplers.py to sd_samplers_compvis.py
2023-01-30 09:35:52 +03:00
0c7c36a6c6
Split history sd_samplers.py to sd_samplers_compvis.py
2023-01-30 09:35:52 +03:00
c81b52ffbd
add override settings component to img2img
2023-01-30 02:40:26 +03:00
847ceae1f7
make it possible to search checkpoint by its hash
2023-01-30 01:41:23 +03:00
399720dac2
update prompt token counts after using the paste params button
2023-01-30 01:03:31 +03:00
f91068f426
change disable_weights_auto_swap to true by default
2023-01-30 00:37:26 +03:00
938578e8a9
make it so that setting options in pasted infotext (like Clip Skip and ENSD) do not get applied directly and instead are added as temporary overrides
2023-01-30 00:25:30 +03:00
425eab3464
Extra network in hr abomination fix
2023-01-29 19:26:31 +03:00
9beeef6267
Extra networks loading fix
2023-01-29 19:16:17 +03:00
6127d2ff1b
Extra networks loading fix
2023-01-29 19:13:27 +03:00
c92ec3a925
Extra networks loading fix
2023-01-29 19:07:00 +03:00
ee3d63b6be
Merge branch 'master' into master
2023-01-29 14:36:10 +03:00
00dab8f10d
remove Batch size and Batch pos from textinfo (goodbye)
2023-01-29 11:53:24 +03:00
aa6e55e001
do not display the message for TI unless the list of loaded embeddings changed
2023-01-29 11:53:05 +03:00
920fe8057c
fixes #7284 btn unbound error
2023-01-29 03:36:16 -05:00
8d7382ab24
add buttons for auto-search in subdirectories for extra tabs
2023-01-29 11:34:58 +03:00
e8efd2ec47
Merge pull request #7353 from EllangoK/preview-fix
...
Fixes thumbnail cards not loading the preview image
2023-01-29 10:41:36 +03:00
659d602dce
only returns ckpt directories if they are not none
2023-01-29 02:32:53 -05:00
f6b7768f84
support for searching subdirectory names for extra networks
2023-01-29 10:20:19 +03:00
09a142a05a
Reduce grid rows if larger than number of images available
...
When a set number of grid rows is specified in settings, then it leads
to situations where an entire row in the grid is empty.
The most noticable example is the processing preview when the row count
is set to 2, where it shows the preview just fine but with a black
rectangle under it.
2023-01-28 19:25:52 -05:00
1d8e06d542
add checkpoints tab for extra networks UI
2023-01-28 22:52:27 +03:00
91c8d0dcfc
Merge pull request #7231 from EllangoK/master
...
Fixes X/Y/Z Plot parameters not being restored from images
2023-01-28 18:45:38 +03:00
fecb990deb
Merge pull request #7309 from brkirch/fix-embeddings
...
Fix embeddings, upscalers, and refactor `--upcast-sampling`
2023-01-28 18:44:36 +03:00
e2c71a4bd4
make prevent the browser from using cached version of scripts when they change
2023-01-28 18:13:03 +03:00
591b68e56c
uses autos new regex, checks len of re_param
2023-01-28 10:04:09 -05:00
cd7e8fb42b
Merge pull request #7319 from Thurion/img2img_batch_fix
...
Fix error when using img2img batch without masks
2023-01-28 17:31:39 +03:00
b7d2af8c7f
add dropdowns in settings for hypernets and loras
2023-01-28 17:18:47 +03:00
1421e95960
allow empty mask dir
2023-01-28 14:42:24 +01:00
5d14f282c2
fixed a bug where after switching to a checkpoint with unknown hash, you'd get empty space instead of checkpoint name in UI
...
fixed a bug where if you update a selected checkpoint on disk and then restart the program, a different checkpoint loads, but the name is shown for the the old one.
2023-01-28 16:23:49 +03:00
f8feeaaedb
add progressbar to extension update check; do not check for updates for disabled extensions
2023-01-28 15:57:56 +03:00
d04e3e921e
automatically detect v-parameterization for SD2 checkpoints
2023-01-28 15:24:41 +03:00
4aa7f5b5b9
update image parameters regex for #7231
2023-01-28 15:24:40 +03:00
f9edd578e9
Remove MPS fix no longer needed for PyTorch
...
The torch.narrow fix was required for nightly PyTorch builds for a while to prevent a hard crash, but newer nightly builds don't have this issue.
2023-01-28 04:16:27 -05:00
ada17dbd7c
Refactor conditional casting, fix upscalers
2023-01-28 04:16:25 -05:00
bea31e849a
Merge pull request #7240 from Unstackd/master
...
Allow users to convert models to Instruct-pix2pix models by supporting merging Instruct-pix2pix models with regular ones in the merge tab
2023-01-28 10:52:28 +03:00
3752aad23d
don't replace regular --help with new paths.py parser help
2023-01-28 02:44:12 -05:00
dc25a31d1a
Gradio Auth Read from External File
...
Usage: `--gradio-auth-path {PATH}`
It adds the credentials to the already existing `--gradio-auth` credentials. It can also handle line breaks.
The file should look like:
`{u1}:{p1},{u2}:{p2}`
or
```
{u1}:{p1},
{u2}:{p2}
```
Will gradio handle duplicate credentials if it happens?
2023-01-27 22:43:10 -08:00
ce72af87d3
Merge pull request #7199 from maxaudron/feature/configurable-data-dir
...
Add flag to store user data sepperate from source code
2023-01-28 09:24:40 +03:00
0834d4ce37
simplify #7284
2023-01-28 08:41:15 +03:00
c99d705e57
Merge pull request #7284 from Gazzoo-byte/patch-1
...
Add button to switch width and height
2023-01-28 08:33:43 +03:00
4c52dfe4ac
make the detection for -v models less broad
2023-01-28 08:30:17 +03:00
41975c375c
Merge pull request #7294 from MrCheeze/model-detection
...
add v2-inpainting model detection, and broaden v-model detection to include anything with 768 in the name
2023-01-28 08:29:01 +03:00
2aac1d9778
Basic inpainting batch support
...
Modifies batch UI to add optional inpainting support
2023-01-27 17:32:31 -08:00
6b82efd737
add v2-inpainting model detection, and broaden v-model detection to include anything with 768 in the name
2023-01-27 20:06:19 -05:00
cc8c9b7474
fix broken calls to find_checkpoint_config
2023-01-27 22:43:08 +03:00
eafaf14167
Add button to switch width and height
...
Adds a button to switch width and height, allowing quick and easy switching between landscape and portrait.
2023-01-27 18:34:41 +00:00
23a9d5e273
create user extensions directory if not exists
2023-01-27 14:44:34 +01:00
6b3981c068
clean up unused script_path imports
2023-01-27 14:44:34 +01:00
14c0884fd0
use python importlib to load and execute extension modules
...
previously module attributes like __file__ where not set correctly,
leading to scripts getting the directory of the stable-diffusion repo
location instead of their own script.
This causes problem when loading user data from an external location
using the --data-dir flag, as extensions would look for their own code
in the stable-diffusion repo location instead of the data dir location.
Using pythons importlib functions sets the modules specs correctly and
executes them. But this will break extensions if they build paths based
on the previously incorrect __file__ attribute.
2023-01-27 14:44:34 +01:00
5eee2ac398
add data-dir flag and set all user data directories based on it
2023-01-27 14:44:30 +01:00
9beb794e0b
clarify the option to disable NaN check.
2023-01-27 13:08:00 +03:00
6f31d2210c
support detecting midas model
...
fix broken api for checkpoint list
2023-01-27 11:54:19 +03:00
d2ac95fa7b
remove the need to place configs near models
2023-01-27 11:28:12 +03:00
7a14c8ab45
add an option to enable sections from extras tab in txt2img/img2img
...
fix some style inconsistenices
2023-01-26 23:31:32 +03:00
cdc2fa209a
Changed filename addition from "instrpix2pix" to the more readable ".instruct-pix2pix" for newly generated instruct pix2pix models.
2023-01-26 11:27:07 -05:00
c4b9b07db6
Fix embeddings dtype mismatch
2023-01-26 09:00:15 -05:00
9e72dc7434
Changed all references to "pix2pix" to the more precise name "instruct pix2pix". Also changed extension to instrpix2pix at least for now.
2023-01-26 06:05:40 -05:00
f90798c6b6
Added error check for the rare case a user merges a pix2pix model with a normal model using weighted sum. Also removed bad print message that interfered with merging progress bar.
2023-01-26 04:38:04 -05:00
f4ec411f2c
Allow checkpoint merger to merge pix2pix models in the same way that it currently supports inpainting models.
2023-01-26 03:45:16 -05:00
10421f93c3
Fix full previews, --no-half-vae
2023-01-26 01:43:35 -05:00
4d634dc592
adds components to infotext_fields
...
allows for loading script params
2023-01-26 00:18:41 -05:00
e57b5f7c55
re_param captures quotes with commas properly
...
and removes unnecessary regex
2023-01-25 22:36:14 -05:00
6cff440182
fix prompt editing break after first batch in img2img
2023-01-25 23:25:40 +03:00
d1d6ce2983
add edit_image_conditioning from my earlier edits in case there's an attempt to inegrate pix2pix properly
...
this allows to use pix2pix model in img2img though it won't work well this way
2023-01-25 23:25:25 +03:00
3cead6983e
Merge pull request #7197 from mcmonkey4eva/fix-ti-symlinks
...
allow symlinks in the textual inversion embeddings folder
2023-01-25 22:59:12 +03:00
15e89ef0f6
fix for unet hijack breaking the train tab
2023-01-25 20:11:01 +03:00
789d47f832
make clicking extra networks button one more time close the extra networks UI
2023-01-25 19:55:31 +03:00
e179b6098a
allow symlinks in the textual inversion embeddings folder
2023-01-25 08:48:40 -08:00
1574e96729
Merge pull request #6510 from brkirch/unet16-upcast-precision
...
Add upcast options, full precision sampling from float16 UNet and upcasting attention for inference using SD 2.1 models without --no-half
2023-01-25 19:12:29 +03:00
57c1baa774
change to code for live preview fix on OSX to be bit more obvious
2023-01-25 18:56:23 +03:00
23dafe6d86
Merge pull request #7151 from brkirch/fix-approx-nn
...
Fix Approx NN previews changing first generation result
2023-01-25 18:48:25 +03:00
ee0a0da324
Add instruct-pix2pix hijack
...
Allows loading instruct-pix2pix models via same method as inpainting models in sd_models.py and sd_hijack_ip2p.py
Adds ddpm_edit.py necessary for instruct-pix2pix
2023-01-25 08:53:23 -05:00
d5ce044bcd
Merge pull request #7146 from EllangoK/master
...
Adds X/Y/Z Grid Script
2023-01-25 11:56:26 +03:00
e3b53fd295
Add UI setting for upcasting attention to float32
...
Adds "Upcast cross attention layer to float32" option in Stable Diffusion settings. This allows for generating images using SD 2.1 models without --no-half or xFormers.
In order to make upcasting cross attention layer optimizations possible it is necessary to indent several sections of code in sd_hijack_optimizations.py so that a context manager can be used to disable autocast. Also, even though Stable Diffusion (and Diffusers) only upcast q and k, unfortunately my findings were that most of the cross attention layer optimizations could not function unless v is upcast also.
2023-01-25 01:13:04 -05:00
84d9ce30cb
Add option for float32 sampling with float16 UNet
...
This also handles type casting so that ROCm and MPS torch devices work correctly without --no-half. One cast is required for deepbooru in deepbooru_model.py, some explicit casting is required for img2img and inpainting. depth_model can't be converted to float16 or it won't work correctly on some systems (it's known to have issues on MPS) so in sd_models.py model.depth_model is removed for model.half().
2023-01-25 01:13:02 -05:00
5228ec8bda
remove fairscale requirement, add fake fairscale to make BLIP not complain about it mk2
2023-01-24 20:30:43 +03:00
28189985e6
remove fairscale requirement, add fake fairscale to make BLIP not complain about it
2023-01-24 20:24:27 +03:00
44c0e6b993
Merge branch 'AUTOMATIC1111:master' into master
2023-01-24 15:44:09 +03:00
e46bfa5a9e
handling sub grids and merging into one
2023-01-24 02:24:32 -05:00
602a1864b0
also return the removed field to sdapi/v1/upscalers because someone might have relied on it existing
2023-01-24 10:09:30 +03:00
42a70d7477
repair sdapi/v1/upscalers returning bogus results
2023-01-24 10:05:45 +03:00
f64af77adc
Fix different first gen with Approx NN previews
...
The loading of the model for approx nn live previews can change the internal state of PyTorch, resulting in a different image. This can be avoided by preloading the approx nn model in advance.
2023-01-23 22:49:20 -05:00
45e270dfc8
add image decod exception handling
2023-01-23 17:11:22 -05:00
5c1cb9263f
fix BLIP failing to import depending on configuration
2023-01-24 00:24:17 +03:00
7ba7f4ed6e
Merge pull request #7113 from vladmandic/interrogate
...
Add selector to interrogate categories
2023-01-24 00:09:14 +03:00
7b1c7ba87b
add support for apostrophe in extra network names
2023-01-23 23:11:34 +03:00
04a561c11c
add option to skip interrogate categories
2023-01-23 12:29:23 -05:00
efa7287be0
Merge branch 'AUTOMATIC1111:master' into interrogate
2023-01-23 12:25:07 -05:00
171a5b3bb9
Merge pull request #7032 from gmq/extra-network-styles
...
Extra network view style
2023-01-23 18:46:37 +03:00
6e1b296baf
api-image-format
2023-01-23 10:10:59 -05:00
e8c3d03f7d
a possible fix for broken image upscaling
2023-01-23 17:59:58 +03:00
925dd09c91
improve interrogate
2023-01-23 09:03:17 -05:00
59146621e2
better support for xformers flash attention on older versions of torch
2023-01-23 16:40:20 +03:00
3fa482076a
Merge remote-tracking branch 'takuma104/xformers-flash-attention'
2023-01-23 16:01:53 +03:00
194cbd065e
fix open directory button failing
2023-01-23 15:50:32 +03:00
663353098e
Merge pull request #7031 from EllangoK/master
...
Fixes various button overflowing UI and compact checkbox
2023-01-23 15:22:06 +03:00
74608300d1
Merge pull request #7093 from Shondoit/fix-dark-mode
...
Fix dark mode
2023-01-23 15:09:26 +03:00
41265a026d
third time's the charm
2023-01-23 14:50:20 +03:00
fabdae089e
add missing import to previous commit
2023-01-23 14:42:49 +03:00
669dbd9725
Fix dark mode
...
Fixes #7048
Co-Authored-By: J.J. Tolton <jjtolton@gmail.com>
2023-01-23 09:54:42 +01:00
b5230197a6
rework extras tab to use script system
2023-01-23 09:24:43 +03:00
f80ff3c1e4
feat(extra-networks): remove view dropdown
2023-01-22 22:01:24 -03:00
66eef11ce7
feat(extra-networks): add default view setting
2023-01-22 12:18:21 -03:00
985c0b8e9a
feat(extra-networks): add thumbs view style
2023-01-22 12:18:21 -03:00
3bc8ee998d
Gen params paste improvement
2023-01-22 16:35:42 +03:00
7f62300f7d
Gen params paste improvement
2023-01-22 16:29:08 +03:00
fccc39834a
Gen params paste improvement
2023-01-22 16:17:55 +03:00
d261bec1ec
Gen params paste improvement
2023-01-22 16:14:28 +03:00
1fa777c1d7
Gen params paste improvement
2023-01-22 16:03:42 +03:00
2aaee73633
Gen params paste improvement
2023-01-22 16:00:35 +03:00
a5c2b5ed89
UI and PNG info improvements
2023-01-22 15:50:20 +03:00
bbb1e35ea2
UI and PNG info improvements
2023-01-22 15:44:59 +03:00
b0ae92d605
UI improvements
2023-01-22 15:43:12 +03:00
68303c96e5
split oversize extras.py to postprocessing.py
2023-01-22 15:38:39 +03:00
34f6d66742
hr conditioning
2023-01-22 15:32:47 +03:00
125d5c8d96
hr conditioning
2023-01-22 15:31:11 +03:00
2ab2bce74d
hr conditioning
2023-01-22 15:28:38 +03:00
c56b367122
Split history extras.py to postprocessing.py
2023-01-22 15:26:41 +03:00
d63340a485
Split history extras.py to postprocessing.py
2023-01-22 15:26:40 +03:00
b238b14ee4
Split history extras.py to postprocessing.py
2023-01-22 15:26:40 +03:00
43ac9ff205
Split history extras.py to postprocessing.py
2023-01-22 15:26:40 +03:00
c5d4c87c02
hr conditioning
2023-01-22 15:17:43 +03:00
4e0cf7d4ed
hr conditioning
2023-01-22 15:15:08 +03:00
a9f0e7d536
hr conditioning
2023-01-22 15:12:00 +03:00
f774a8d24e
Hr-fix separate prompt experimentation
2023-01-22 14:52:01 +03:00
81e0723d65
Logging for debugging
2023-01-22 14:41:41 +03:00
b331ca784a
Fix
2023-01-22 14:35:34 +03:00
8114959e7e
Hr separate prompt test
2023-01-22 14:28:53 +03:00
c98cb0f8ec
amend previous commit to work in a proper fashion when saving previews
2023-01-22 11:04:02 +03:00
35419b2746
add an option to reorder tabs for extra networks
2023-01-22 11:00:05 +03:00
112416d041
add option to discard weights in checkpoint merger UI
2023-01-22 10:17:12 +03:00
0792fae078
fix missing field for aesthetic embedding extension
2023-01-22 08:20:48 +03:00
2621566153
attention ctrl+up/down enhancements
2023-01-22 08:07:18 +03:00
bf457b30fb
compact checkbox and fix copy image btn overflow
...
also fixes type for #tab_extensions in style.css
2023-01-21 16:21:33 -05:00
f7b38c4841
Style fix
2023-01-22 00:18:26 +03:00
f2eae6127d
fix broken textual inversion extras tab
2023-01-22 00:16:26 +03:00
0f6862ef30
PLMS edge-case handling fix 5
2023-01-22 00:11:05 +03:00
6cd7bf9f86
PLMS edge-case handling fix 3
2023-01-22 00:08:58 +03:00
3ffe2e768b
PLMS edge-case handling fix 2
2023-01-22 00:07:46 +03:00
9e1f49c4e5
PLMS edge-case handling fix
2023-01-22 00:03:16 +03:00
fe7a623e6b
add a slider for default value of added extra networks
2023-01-22 00:02:52 +03:00
78f59a4e01
enable compact view for train tab
...
prevent previews from ruining hypernetwork training
2023-01-22 00:02:51 +03:00
8bec3a2aa1
Index fix
2023-01-21 23:31:36 +03:00
6c0566f937
Type mismatch fix
2023-01-21 23:25:36 +03:00
abf11215e0
Merge pull request #6955 from EllangoK/master
...
Adds descriptions for merging methods in UI
2023-01-21 23:17:06 +03:00
3bd898b6ce
First test of different sampler for hi-res fix
2023-01-21 23:14:59 +03:00
4a8fe09652
remove the double loading text
2023-01-21 23:06:18 +03:00
e4e0918f58
remove timestamp for js files, reformat code
2023-01-21 22:57:19 +03:00
7c8852b8e7
Merge pull request #7015 from jjtolton/serve-static-js
...
Compile and serve js files via `src` instead of embedded inline scripts
2023-01-21 22:43:18 +03:00
035459c9a2
remove dead import
2023-01-21 14:11:13 -05:00
50059ea661
server individually listed javascript files vs single compiled file
2023-01-21 14:07:48 -05:00
17af0fb955
remove commented out lines
2023-01-21 13:27:05 -05:00
f726df8a2f
Compile and serve js from /statica instead of inline in html
2023-01-21 12:59:05 -05:00
f53527f778
make it run on gradio < 3.16.2
2023-01-21 20:07:14 +03:00
3deea34135
extract extra network data from prompt earlier
2023-01-21 19:36:08 +03:00
63b824376c
add --gradio-queue option to enable gradio queue
2023-01-21 18:47:54 +03:00
424cefe118
add search box to extra networks
2023-01-21 17:20:24 +03:00
92fb1096db
make it so that extra networks are not removed from infotext
2023-01-21 16:41:25 +03:00
855b9e3d1c
Lora support!
...
update readme to reflect some recent changes
2023-01-21 16:15:53 +03:00
3262e825cc
add --xformers-flash-attention option & impl
2023-01-21 17:42:04 +09:00
184e23eb89
relocate tool buttons next to generate button
...
prevent extra network tabs from putting images into wrong prompts
prevent settings leaking into prompt
2023-01-21 09:58:57 +03:00
6d805b669e
make CLIP interrogator download original text files if the directory does not exist
...
remove random artist built-in extension (to re-added as a normal extension on demand)
remove artists.csv (but what does it mean????????????????????)
make interrogate buttons show Loading... when you click them
2023-01-21 09:14:27 +03:00
40ff6db532
extra networks UI
...
rework of hypernets: rather than via settings, hypernets are added directly to prompt as <hypernet:name:weight>
2023-01-21 08:36:07 +03:00
20a59ab3b1
move token counter to the location of the prompt, add token counting for the negative prompt
2023-01-20 10:18:41 +03:00
98466da4bc
adds descriptions for merging methods in ui
2023-01-20 00:48:15 -05:00
6c7a50d783
remove some unnecessary logging to javascript console
2023-01-20 08:36:37 +03:00
6073456c83
write a comment for fix_checkpoint function
2023-01-19 20:39:10 +03:00
51517f3ea6
Merge pull request #6936 from EllangoK/master
...
Fixes minor typos around run_modelmerger
2023-01-19 19:58:16 +03:00
AUTOMATIC