963d986396
Merge branch 'AUTOMATIC1111:master' into deepdanbooru_pre_process
2022-10-11 17:33:15 -05:00
d4ea5f4d86
add an option to unload models during hypernetwork training to save VRAM
2022-10-11 19:03:08 +03:00
c0484f1b98
Add cross-attention optimization from InvokeAI
...
* Add cross-attention optimization from InvokeAI (~30% speed improvement on MPS)
* Add command line option for it
* Make it default when CUDA is unavailable
2022-10-11 17:24:00 +03:00
873efeed49
rename hypernetwork dir to hypernetworks to prevent clash with an old filename that people who use zip instead of git clone will have
2022-10-11 15:51:30 +03:00
5992564448
Cleaned ngrok integration
2022-10-11 15:38:53 +03:00
530103b586
fixes related to merge
2022-10-11 14:53:02 +03:00
5e2627a1a6
Comma backtrack padding ( #2192 )
...
Comma backtrack padding
2022-10-11 09:55:28 +03:00
8617396c6d
Added slider for deepbooru score threshold in settings
2022-10-11 09:43:16 +03:00
47f5e216da
Merge branch 'deepdanbooru_pre_process' into master
2022-10-10 18:10:49 -05:00
76ef3d75f6
added deepbooru settings (threshold and sort by alpha or likelyhood)
2022-10-10 18:01:49 -05:00
f98338faa8
add an option to not add watermark to created images
2022-10-10 23:15:48 +03:00
b3d3b335cf
Merge pull request #2131 from ssysm/upstream-master
...
Add VAE Path Arguments
2022-10-10 20:45:14 +03:00
39919c40dd
add eta noise seed delta option
2022-10-10 20:32:44 +03:00
7349088d32
--no-half-vae
2022-10-10 16:16:29 +03:00
6fdad291bd
Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webui into upstream-master
2022-10-09 23:20:39 -04:00
cc92dc1f8d
add vae path args
2022-10-09 23:17:29 -04:00
a14f7bf113
Corrected CLIP Layer Ignore description and updated its range to the max possible
2022-10-09 22:31:23 +03:00
6c383d2e82
show model selection setting on top of page
2022-10-09 22:24:07 +03:00
875ddfeecf
added guard for torch.load to prevent loading pickles with unknown content
2022-10-09 17:58:43 +03:00
e6e8cabe0c
change up #2056 to make it work how i want it to plus make xy plot write correct values to images
2022-10-09 14:57:48 +03:00
d6d10a37bf
Added extended model details to infotext
2022-10-09 14:49:15 +03:00
1ffeb42d38
Fix typo
2022-10-09 11:10:13 +03:00
122d42687b
Fix VRAM Issue by only loading in hypernetwork when selected in settings
2022-10-09 11:08:11 +03:00
e00b4df7c6
Merge pull request #1752 from Greendayle/dev/deepdanbooru
...
Added DeepDanbooru interrogator
2022-10-09 10:52:21 +03:00
432782163a
chore: Fix typos
2022-10-08 22:42:30 +03:00
1371d7608b
Added ability to ignore last n layers in FrozenCLIPEmbedder
2022-10-08 22:10:37 +03:00
0ec80f0125
Merge branch 'master' into dev/deepdanbooru
2022-10-08 18:28:22 +02:00
3061cdb7b6
add --force-enable-xformers option and also add messages to console regarding cross attention optimizations
2022-10-08 19:22:15 +03:00
01f8cb4447
made deepdanbooru optional, added to readme, automatic download of deepbooru model
2022-10-08 18:02:56 +02:00
dc1117233e
simplify xfrmers options: --xformers to enable and that's it
2022-10-08 17:02:18 +03:00
48feae37ff
Merge pull request #1851 from C43H66N12O12S2/flash
...
xformers attention
2022-10-08 16:29:59 +03:00
ddfa9a9786
add xformers_available shared variable
2022-10-08 16:20:41 +03:00
4999eb2ef9
do not let user choose his own prompt token count limit
2022-10-08 14:25:47 +03:00
00117a07ef
check specifically for skipped
2022-10-08 13:40:39 +03:00
786d9f63aa
Add button to skip the current iteration
2022-10-08 13:40:39 +03:00
706d5944a0
let user choose his own prompt token count limit
2022-10-08 13:38:57 +03:00
bad7cb29ce
added support for hypernetworks (???)
2022-10-07 10:17:52 +03:00
da4ab2707b
Update shared.py
2022-10-07 05:23:06 +03:00
cf7c784fcc
Removed duplicate defined models_path
...
Use `modules.paths.models_path` instead `modules.shared.model_path`.
2022-10-06 20:29:12 +03:00
fec71e4de2
Default window title progress updates on
2022-10-06 17:58:52 +03:00
be71115b1a
Update shared.py
2022-10-06 17:58:52 +03:00
5993df24a1
integrate the new samplers PR
2022-10-06 14:12:52 +03:00
3ddf80a9db
add variant setting
2022-10-06 13:42:21 +03:00
5f24b7bcf4
option to let users select which samplers they want to hide
2022-10-06 12:08:59 +03:00
55400c981b
Set gradio-img2img-tool default to 'editor'
2022-10-06 08:46:32 +03:00
b32852ef03
add editor to img2img
2022-10-04 20:49:54 +03:00
957e29a8e9
option to not show images in web ui
2022-10-04 17:23:48 +03:00
ea6b0d98a6
Remove pycharm note, fix typo
2022-10-04 15:21:34 +03:00
accd00d6b8
Explain how to use second progress bar in pycharm
2022-10-04 15:21:34 +03:00
dc9c5a9774
Modify --add-cpu description
2022-10-04 05:22:50 -04:00
27ddc24fde
Add BSRGAN to --add-cpu
2022-10-04 05:18:17 -04:00
eeab7aedf5
Add --use-cpu command line option
...
Remove MPS detection to use CPU for GFPGAN / CodeFormer and add a --use-cpu command line option.
2022-10-04 04:24:35 -04:00
138662734c
use dropdown instead of radio for img2img upscaler selection
2022-10-03 07:57:59 +03:00
c4445225f7
change wording for options
2022-10-02 21:50:14 +03:00
91f327f22b
make save to dirs optional for imgs saved from ui
2022-10-02 21:47:52 +03:00
3ff0de2c59
added --disable-console-progressbars to disable progressbars in console
...
disabled printing prompts to console by default, enabled by --enable-console-prompts
2022-10-02 20:23:40 +03:00
5d26ba2b4b
Merge branch 'master' into ScuNET
2022-10-02 07:56:22 -05:00
820f1dc96b
initial support for training textual inversion
2022-10-02 15:03:39 +03:00
8deae07700
Add ScuNET DeNoiser/Upscaler
...
Q&D Implementation of ScuNET, thanks to our handy model loader. :P
https://github.com/cszn/SCUNet
2022-09-30 15:28:37 -05:00
2b03f0bbda
if --ckpt option is specified, load that model
2022-09-30 22:16:03 +03:00
b60cd0809f
return the dropdown that mysteriously disappeared
2022-09-30 12:56:36 +03:00
d1f098540a
remove unwanted formatting/functionality from the PR
2022-09-30 11:42:40 +03:00
d73741794d
Merge remote-tracking branch 'upstream/master' into ModelLoader
2022-09-29 19:59:36 -05:00
0dce0df1ee
Holy $hit.
...
Yep.
Fix gfpgan_model_arch requirement(s).
Add Upscaler base class, move from images.
Add a lot of methods to Upscaler.
Re-work all the child upscalers to be proper classes.
Add BSRGAN scaler.
Add ldsr_model_arch class, removing the dependency for another repo that just uses regular latent-diffusion stuff.
Add one universal method that will always find and load new upscaler models without having to add new "setup_model" calls. Still need to add command line params, but that could probably be automated.
Add a "self.scale" property to all Upscalers so the scalers themselves can do "things" in response to the requested upscaling size.
Ensure LDSR doesn't get stuck in a longer loop of "upscale/downscale/upscale" as we try to reach the target upscale size.
Add typehints for IDE sanity.
PEP-8 improvements.
Moar.
2022-09-29 17:46:23 -05:00
c1c27dad3b
new implementation for attention/emphasis
2022-09-29 11:31:48 +03:00
7acfaca05a
update lists of models after merging them in checkpoints tab
...
support saving as half
2022-09-29 00:59:44 +03:00
d64b451681
added support for automatically installing latest k-diffusion
...
added eta parameter to parameters output for generated images
split eta settings into ancestral and ddim (because they have different default values)
2022-09-28 18:09:06 +03:00
aea5b2510e
save parameters for images when using the Save button.
2022-09-28 17:05:23 +03:00
047ca73388
Update shared.py
2022-09-28 05:11:40 +03:00
5756d517a6
Merge remote-tracking branch 'upstream/master' into ModelLoader
2022-09-27 11:02:41 -05:00
11875f5863
Use model loader with stable-diffusion too.
...
Hook the model loader into the SD_models file.
Add default url/download if checkpoint is not found.
Add matching stablediffusion-models-path argument.
Add message that --ckpt-dir will be removed in the future, but have it pipe to stablediffusion-models-path for now.
Update help strings for models-path args so they're more or less uniform.
Move sd_model "setup" call to webUI with the others.
Ensure "cleanup_models" method moves existing models to the new locations, including SD, and that we aren't deleting folders that still have stuff in them.
2022-09-27 11:01:13 -05:00
c055132606
Fix downssample typo in options
...
Updated `downssample` to `down-sample`, matching spelling in other places.
2022-09-27 09:50:06 -04:00
61585e5778
rename DDIM eta label
2022-09-27 09:30:45 +03:00
6b78833e33
Add extra kdiffusion parameters
2022-09-27 09:30:45 +03:00
619668ccfe
Add options for exposed ddim sampler params
...
ddim_eta & ddim_discretize
2022-09-27 09:30:45 +03:00
16e7ac09df
job_timestamp initialization change
2022-09-27 08:51:59 +03:00
740070ea9c
Re-implement universal model loading
2022-09-26 09:29:50 -05:00
1877a3767e
Changed job_id to timestamp
2022-09-25 17:11:07 +03:00
4c3d4aad60
fix formatting
2022-09-25 17:11:07 +03:00
e13912dfde
fix formatting
2022-09-25 17:11:07 +03:00
40166dbf08
Added job_id pattern for directories
2022-09-25 17:11:07 +03:00
b5d705e263
Disable 'batch img2img' when launched with --hide-ui-dir-config
...
Prevent writing to arbitrary directories, as usual
2022-09-24 19:06:36 +03:00
ed8b8b3b8c
Fix to XY_Grid script console progress bar and other progress bar improvements ( #890 )
...
Fix to XY_Grid script console progress bar and other progress bar improvements #890
2022-09-24 08:09:59 +03:00
1a0353675d
Option to use advanced upscalers with normal img2img
2022-09-23 17:37:47 +03:00
6fa20d51dc
prevent saving settings with bogus values
2022-09-23 17:27:30 +03:00
79e7c39298
Merge pull request #847 from rewbs/rewbs-optionally-save-before-color-correction
...
Add option to save before color correction. This helps with some posterisation issues in img2img loopback.
2022-09-23 14:41:06 +03:00
d4205e66fa
gfpgan: just download the damn model
2022-09-23 10:26:00 +03:00
7ef361dfc3
add warning for when user's settings are broken
2022-09-23 09:15:00 +03:00
03738668c0
Merge from master
2022-09-23 00:54:32 +00:00
77cf346d93
settings categories split to columns, remade categories
2022-09-22 21:32:44 +03:00
75b90a5e40
emergency fix for the settings screen breaking the program
2022-09-22 20:41:22 +03:00
dec7584903
Add Section keys and headers to settings
2022-09-22 20:26:21 +03:00
ae32b8a53f
Fixed directory name generation process.
...
'Max prompt words' has been added to config and modified to be used in the directory name generation process.
2022-09-22 20:15:37 +03:00
a213d3a21c
Add option to always log generation info
2022-09-22 16:34:54 +03:00
25eb1e3d90
Add option to save before color correction. Add suffix param when saving files, used for special saves without color correction and face restoration.
2022-09-22 20:54:50 +10:00
91bfc71261
A big rework, just what you were secretly hoping for!
...
SD upscale moved to scripts
Batch processing script removed
Batch processing added to main img2img and now works with scripts
img2img page UI reworked to use tabs
2022-09-22 12:11:48 +03:00
3eaae8ae65
reworking #775
2022-09-22 07:59:27 +03:00
c214c428bc
Basic settings for realesrgan model selection.
...
I don't like that you have to restart the app, but it works.
2022-09-22 07:21:54 +03:00
1a1f7e85c7
Add LDSR and "GoLatent?" Upscaling ( #763 )
...
* Add LDSR Upscaling
2022-09-21 16:06:37 +03:00
4b26b50df0
Merge remote-tracking branch 'origin/master'
2022-09-21 09:49:07 +03:00
254da5d127
--opt-split-attention now on by default for torch.cuda, off for others (cpu and MPS; because the option does not work there according to reports)
2022-09-21 09:49:02 +03:00
29d6084f47
disallow no tiling as we don't support it
2022-09-21 09:09:39 +03:00
403bb02948
breakout tile options
2022-09-21 09:09:39 +03:00
55dc847c48
Update shared.py
2022-09-20 23:31:06 +03:00
19a75d38d7
added --use-textbox-seed option to make long seeds possible from web ui
2022-09-20 20:10:01 +03:00
06cd206107
Enable neural network upscalers for highres. fix
2022-09-20 19:32:26 +03:00
06e076e48a
Keep legacy behaviour wrt reuse of filename during batch processes
2022-09-20 07:44:19 +03:00
5fe2c75da0
Support reusing filename stems during batch processing in Extras tab
2022-09-20 07:44:19 +03:00
53651696dc
avoid exception if empty
2022-09-19 22:49:53 +03:00
acbe44b835
automatically match any version gfpgan
2022-09-19 22:49:53 +03:00
028fc25f28
fix the issue with incorrect js options on page load
...
add a setting for lightbox max size images
use setting for lightbox max size images late to let user change it and see results
2022-09-19 17:16:04 +03:00
1878994f9b
fix grammer
2022-09-19 00:40:30 +03:00
21244f50c4
fix some typos and remove unused import
2022-09-19 00:40:30 +03:00
cfb6cc8ce5
replace argparse.BooleanOptionalAction with 'store_true'
2022-09-18 23:06:49 +03:00
f3965cce01
added command line argument --autolaunch to open the webui URL in the system's default browser upon launch (implements #274 )
2022-09-18 22:39:34 +03:00
f3d83fd68a
add read access to settings for jsavascript
...
add an option to disable lightbox modal
2022-09-18 22:25:18 +03:00
cae5c5fa8d
Making opt split attention the default. Are you upset about this? Sorry.
2022-09-18 20:55:46 +03:00
3f29aa791b
altered progressbar to not rely on first progress request coming after the job has started; may help with broken progressbar some people say they have
2022-09-18 11:14:42 +03:00
247f58a5e7
add support for switching model checkpoints at runtime
2022-09-17 12:05:18 +03:00
ed6787ca2f
Add VRAM monitoring
2022-09-17 09:15:16 +03:00
e49b1c5d73
an option to do exactly the amount of specified steps in img2img
2022-09-16 13:38:02 +03:00
83bce1a604
Merge branch 'batch-seed-attempt'
2022-09-16 09:48:46 +03:00
87e8b9a2ab
prevent replacing torch_randn globally (instead replacing k_diffusion.sampling.torch) and add a setting to disable this all
2022-09-16 09:47:03 +03:00
d7f7378828
quantization off by default
2022-09-15 14:55:38 +03:00
829d7150bc
Add setting for quantization
2022-09-15 14:54:52 +03:00
4a626f6ea6
Corrected typos in shared.py and README
2022-09-15 07:38:17 +03:00
5dde56afe3
Fixed typo in text attention setting
2022-09-14 18:41:40 +03:00
9f267af3f7
added a second style field
...
added the ability to use {prompt} in styles
added a button to apply style to textbox
rearranged top row for UI
2022-09-14 17:56:21 +03:00
4c51752464
option name updates for #432
2022-09-14 11:31:49 +03:00
74c5f7974c
Added selected image saving
2022-09-14 11:27:41 +03:00
f07d789b79
added cmd arg to load custom styles file
2022-09-14 08:48:42 +03:00
950064ee96
img2img_color_correction off by default for #394
2022-09-13 20:00:19 +03:00
c84e333622
color correction option for all img2img modes #363
2022-09-13 12:51:57 +03:00
823cf946ec
Embeddings directory can't be found if running webui.py from another directory (+potential fix) #374
2022-09-13 09:42:51 +03:00
fc18e2d483
Adds NSFW content filter option
2022-09-12 19:15:35 -05:00
db8f8dd972
Ability to save images into a folder named after the date they were created #353
2022-09-13 00:44:08 +03:00
3de44fc580
Include the model name (or the SHA256 of the file) in the metadata #271
2022-09-12 20:47:46 +03:00
c7e0e28ccd
changes for #294
2022-09-12 20:09:32 +03:00
11e03b9abd
Merge pull request #294 from EliasOenal/master
...
Fixes for mps/Metal: use of seeds, img2img, CodeFormer
2022-09-12 19:58:06 +03:00
843b2b64fc
Instance of CUDA out of memory on a low-res batch, even with --opt-split-attention-v1 (found cause) #255
2022-09-12 18:40:06 +03:00
40f4d3ed98
[FEATURE] Save both images, (Skip_Save optional). #265
2022-09-12 17:47:36 +03:00
b7f95869b4
Refactored Metal/mps fixes.
2022-09-12 16:32:44 +02:00
a5a760a7d4
rename --channelslast to --opt-channelslast to be in line with other torch optimizations
2022-09-12 16:43:11 +03:00
8c995be44d
Add cmd option for channels last
2022-09-12 16:27:23 +03:00
264d255919
Merge pull request #329 from EyeDeck/master
...
Add --gradio-auth command line argument to enable Gradio authentication
2022-09-12 15:45:11 +03:00
a4416f3585
[BUG] Not Working As Intended - create a directory with name derived from the prompt #306
2022-09-12 15:41:30 +03:00
fc49844aa8
Merge branch 'master' into master
2022-09-12 08:19:14 -04:00
372a2c3e2e
[Feature Request] Please add "--share-password" for Gradio server security #315
2022-09-12 15:10:05 +03:00
e3646e79aa
Add --auth command line argument to enable Gradio authentication
...
Allows you to pass in Gradio authentication like:
`--auth username:password`
Supports multiple sets of credentials by comma-delimiting, like:
`--auth user1:pass1,user2:pass3`...
2022-09-12 08:08:41 -04:00
c094f00e10
Merge branch 'master' into master
2022-09-12 13:23:58 +03:00
ddc86f2edb
--gradio-debug for collab users
2022-09-12 12:40:55 +03:00
e68484500f
Merge remote-tracking branch 'origin/master'
2022-09-12 11:55:35 +03:00
9bb20be090
memory optimization for CLIP interrogator
...
changed default cfg_scale to a higher value
2022-09-12 11:55:27 +03:00
655ef8e8cb
Added cmd arg to load custom ui settings file
2022-09-12 10:20:38 +03:00
ab0a79cdf4
keep interrogate models not in vram by default
2022-09-12 09:00:11 +03:00
e05e46aa3f
Merge branch 'master' into master
2022-09-11 18:15:30 -04:00
4535239d8a
Add a samples filename format option
...
Adds a "samples filename format" option in the settings. This format can be defined by tags for maximum flexibility and scalability.
2022-09-11 23:25:20 +03:00
29a2933e23
Add --hide-ui-dir-config command line flag
...
Adds `--hide-ui-dir-config` flag to disable editing directory configs from the web UI. This can be set to prevent users from setting the directory to somewhere they shouldn't, for public (or semi-public) interfaces.
Directories are still read from config.json, so the server admin can still set them in the web UI and then relaunch with the hide flag, or edit the config manually.
Also:
- fix OptionInfo `component_args` keyword argument not being read if `component` isn't also set
- ensure that hidden settings aren't still read from the web UI (otherwise they could still be changed by tampering with the interface)
2022-09-11 16:00:42 -04:00
f194457229
CLIP interrogator
2022-09-11 18:48:36 +03:00
b5d1af11b7
Modular device management
2022-09-11 09:49:43 +03:00
06fadd2dc5
added --opt-split-attention-v1
2022-09-11 00:29:10 +03:00
43bdbe934a
enabled negative prompt by default
...
fixed broken empty directory when prompt does not start withl etter
2022-09-10 15:41:29 +03:00
decbbe81f5
separated options for sample and grid dir saving for #222
2022-09-10 13:36:16 +03:00
955f644ce1
split settings into three columns
...
added a different workaround for gradio mask bug with info in UI
switched to newer gradio version
2022-09-10 11:10:00 +03:00
26ce47eb6c
[Feature Request] Ability to pass a custom ui-config.json via command line args #212
2022-09-10 08:18:54 +03:00
79cca25704
Embed roboto
2022-09-09 23:27:18 +03:00
86867e153f
support for prompt styles
...
fix broken prompt matrix
2022-09-09 23:16:02 +03:00
b1707553cf
added resize seeds and variation seeds features
2022-09-09 17:54:04 +03:00
003b60b94e
add an option to show negative prompt
2022-09-09 09:15:36 +03:00
bcb8a5eb0a
change default font capitalization to possibly help linux users #157
2022-09-09 08:45:39 +03:00
764a64b02e
Some typos
2022-09-09 01:17:38 +02:00
f211c498b9
More informative progress printing
2022-09-08 17:05:17 +02:00
f5001246e2
honor tiling settings for RealESRGAN also
...
load scripts earlier to get errors before model loads
2022-09-08 15:19:36 +03:00
567c1fbc1c
Port defaults to none
2022-09-08 10:42:21 +02:00
db92896e30
help message for ports < 1024
2022-09-08 09:47:56 +02:00
5d087731a5
add --port argument to shared.py
...
defaults to 7860
2022-09-08 09:44:14 +02:00
65fbefd033
Added support for launching on Apple Silicon
2022-09-07 15:58:25 +02:00
15bb8e8057
labeling updates according to anon's feedback
2022-09-07 13:46:08 +03:00
5e12c23a67
clarification for settings; another comment about copied files
2022-09-07 12:57:12 +03:00
6a9b33c848
codeformer support
2022-09-07 12:32:28 +03:00
6521f90fa2
add a font for google collab
2022-09-07 02:18:45 +03:00
23ee74e9e3
fix error with --help #91
2022-09-07 02:08:11 +03:00
7ce7fb01e0
fix for live progress breaking lowvram and medvram optimizations
2022-09-06 23:10:12 +03:00
7e5b8becf9
fix for progress bar
2022-09-06 20:26:09 +03:00
fd66199769
added preview option
2022-09-06 19:33:51 +03:00
3f55d9a932
collab link
2022-09-06 10:58:58 +03:00
c688d0984e
some extra changes for collab compatibility
2022-09-06 10:38:02 +03:00
395f170597
readme extras for VRAM for
...
added missing packages to requirements for #74
add support for negative numbers in X/Y plot (plus ranges) #73
changed progressbar to work properly with custom modes
2022-09-06 10:11:25 +03:00
a243bc7859
added progressbar
...
added an option to disable progressbar
added interrupt support to DDIM/PLMS
2022-09-06 02:09:01 +03:00
b6763fb884
added random artist button
...
added a setting for padding when doing inpaint at original resolution
2022-09-05 23:08:06 +03:00
064965c466
added --listen option to make gradio listen on network requests
2022-09-05 19:37:11 +03:00
a8a58dbac7
re-integrated tiling option as a UI element
2022-09-05 03:25:37 +03:00
f91d0c3d19
add an option to enable tiling image generation
2022-09-05 02:16:36 +03:00
a039878c0f
bugfix (thx #88443949 )
2022-09-05 02:02:15 +03:00
5bb126bd89
add split attention layer optimization from https://github.com/basujindal/stable-diffusion/pull/117
2022-09-05 01:41:20 +03:00
f299645aee
ESRGAN support
2022-09-04 18:54:12 +03:00
595c827bd3
option to unload GFPGAN after using
2022-09-03 17:28:30 +03:00
f40617d6c4
support for scripts
2022-09-03 17:21:15 +03:00
345028099d
split codebase into multiple files; to anyone this affects negatively: sorry
2022-09-03 12:08:45 +03:00
JC-Array