616b7218f7
fix: handles when state_dict does not exist
3 years ago
91d66f5520
use new attnblock for xformers path
3 years ago
76a616fa6b
Update sd_hijack_optimizations.py
3 years ago
5d54f35c58
add xformers attnblock and hypernetwork support
3 years ago
f2055cb1d4
Add hypernetwork support to split cross attention v1
...
* Add hypernetwork support to split_cross_attention_forward_v1
* Fix device check in esrgan_model.py to use devices.device_esrgan instead of shared.device
3 years ago
b70eaeb200
delete broken and unnecessary aliases
3 years ago
c9cc65b201
switch to the proper way of calling xformers
3 years ago
12c4d5c6b5
hypernetwork training mk1
3 years ago
5f12e7efd9
linux test
3 years ago
fa2ea648db
even more powerfull fix
3 years ago
54fa613c83
loading tf only in interrogation process
3 years ago
537da7a304
Merge branch 'master' into dev/deepdanbooru
3 years ago
f7c787eb7c
make it possible to use hypernetworks without opt split attention
3 years ago
97bc0b9504
do not stop working on failed hypernetwork load
3 years ago
d15b3ec001
support loading VAE
3 years ago
bad7cb29ce
added support for hypernetworks (???)
3 years ago
5e3ff846c5
Update sd_hijack.py
3 years ago
5303df2428
Update sd_hijack.py
3 years ago
35d6b23162
Update sd_hijack.py
3 years ago
da4ab2707b
Update shared.py
3 years ago
2eb911b056
Update sd_hijack.py
3 years ago
f174fb2922
add xformers attention
3 years ago
b34b25b4c9
karras samplers for img2img?
3 years ago
405c8171d1
Prefer using `Processed.sd_model_hash` attribute when filename pattern
3 years ago
1cc36d170a
Added job_timestamp to Processed
...
So `[job_timestamp]` pattern can use in saving image UI.
3 years ago
070b7d60cf
Added styles to Processed
...
So `[styles]` pattern can use in saving image UI.
3 years ago
cf7c784fcc
Removed duplicate defined models_path
...
Use `modules.paths.models_path` instead `modules.shared.model_path`.
3 years ago
dbc8a4d351
add generation parameters to images shown in web ui
3 years ago
0bb458f0ca
Removed duplicate image saving codes
...
Use `modules.images.save_image()` instead.
3 years ago
b66aa334a9
Merge branch 'master' into fix-vram
3 years ago
fec71e4de2
Default window title progress updates on
3 years ago
be71115b1a
Update shared.py
3 years ago
5993df24a1
integrate the new samplers PR
3 years ago
3ddf80a9db
add variant setting
3 years ago
71901b3d3b
add karras scheduling variants
3 years ago
2d3ea42a2d
workaround for a mysterious bug where prompt weights can't be matched
3 years ago
5f24b7bcf4
option to let users select which samplers they want to hide
3 years ago
4288e53fc2
removed unused import, fixed typo
3 years ago
2499fb4e19
Add sanitizer for captions in Textual inversion
3 years ago
0e92c36707
Merge pull request #1755 from AUTOMATIC1111/use-typing-list
...
use typing.list in prompt_parser.py for wider python version support
3 years ago
55400c981b
Set gradio-img2img-tool default to 'editor'
3 years ago
af02ee1297
Merge branch 'master' into use-typing-list
3 years ago
34c358d10d
use typing.list in prompt_parser.py for wider python version support
3 years ago
20f8ec877a
remove type annotations in new code because presumably they don't work in 3.7
3 years ago
f8e41a96bb
fix various float parsing errors
3 years ago
4320f386d9
removing underscores and colons
3 years ago
c26732fbee
added support for AND from https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/
3 years ago
17a99baf0c
better model search
3 years ago
1506fab29a
removing problematic tag
3 years ago
59a2b9e5af
deepdanbooru interrogator
3 years ago
bbdbbd36ed
shared.state.interrupt when restart is requested
3 years ago
82380d9ac1
Removing parts no longer needed to fix vram
3 years ago
1f50971fb8
Merge branch 'master' into fix-vram
3 years ago
ef40e4cd4d
Display time taken in mins, secs when relevant
...
Fixes #1656
3 years ago
b32852ef03
add editor to img2img
3 years ago
90e911fd54
prompt_parser: allow spaces in schedules, add test, log/ignore errors
...
Only build the parser once (at import time) instead of for each step.
doctest is run by simply executing modules/prompt_parser.py
3 years ago
1eb588cbf1
remove functools.cache as some people are having issues with it
3 years ago
e1b128d8e4
do not touch p.seed/p.subseed during processing #1181
3 years ago
957e29a8e9
option to not show images in web ui
3 years ago
52cef36f6b
emergency fix for img2img
3 years ago
e6cbef785a
Merge pull request #1550 from RnDMonkey/#1484_fix_empty_styles_pattern
...
#1484 fix empty styles pattern
3 years ago
eec1b39bd5
Apply prompt pattern last
3 years ago
ea6b0d98a6
Remove pycharm note, fix typo
3 years ago
accd00d6b8
Explain how to use second progress bar in pycharm
3 years ago
e9e2a7ec9a
Merge branch 'master' into cpu-cmdline-opt
3 years ago
d5bba20a58
ignore errors in parse for purposes of token counting for #1564
3 years ago
b7f3996982
Merge remote-tracking branch 'origin/master'
3 years ago
6165246124
support interrupting after the previous change
3 years ago
2f1b61d979
Allow nested structures inside schedules
3 years ago
6c6ae28bf5
send all three of GFPGAN's and codeformer's models to CPU memory instead of just one for #1283
3 years ago
dc9c5a9774
Modify --add-cpu description
3 years ago
27ddc24fde
Add BSRGAN to --add-cpu
3 years ago
2adb249740
Merge branch 'cpu-cmdline-opt' of https://github.com/brkirch/stable-diffusion-webui into cpu-cmdline-opt
3 years ago
35a00b0130
Merge branch 'AUTOMATIC1111:master' into cpu-cmdline-opt
3 years ago
eeab7aedf5
Add --use-cpu command line option
...
Remove MPS detection to use CPU for GFPGAN / CodeFormer and add a --use-cpu command line option.
3 years ago
5ef0baf5ea
add support for gelbooru tags in filenames for textual inversion
3 years ago
b88e4ea7d6
Merge branch 'master' into master
3 years ago
2865ef4b9a
fix broken date in TI
3 years ago
43a74fa595
batch processing for img2img with an empty output directory, by request
3 years ago
d15c125db7
Merge remote-tracking branch 'origin/master'
3 years ago
6491b09c24
use existing function for gfpgan
3 years ago
80c418c0d3
Merge branch 'AUTOMATIC1111:master' into #1484_fix_empty_styles_pattern
3 years ago
36ea4ac0f5
moved no-style return outside join function
3 years ago
34c638142e
Fixed when eta = 0
...
Unexpected behavior when using eta = 0 in something like XY, but your default eta was set to something not 0.
3 years ago
e615d4f9d1
Convert folder icon surrogate pair to valid utf8
3 years ago
2cd6a00f37
Merge remote-tracking branch 'origin/master'
3 years ago
138662734c
use dropdown instead of radio for img2img upscaler selection
3 years ago
3fac3764b3
Merge branch 'master' into #1484_fix_empty_styles_pattern
3 years ago
ad0cc85d1f
Merge branch 'master' into stable
3 years ago
166283653c
remove LDSR warning
3 years ago
6785331e22
keep textual inversion dataset latents in CPU memory to save a bit of VRAM
3 years ago
c7543d4940
preprocessing for textual inversion added
3 years ago
c4445225f7
change wording for options
3 years ago
91f327f22b
make save to dirs optional for imgs saved from ui
3 years ago
688c4a914a
Merge branch 'master' into 1404-script-reload-without-restart
3 years ago
e808096cf6
correct indent
3 years ago
852fd90c0d
emergency fix for disabling SD model download after multiple complaints
3 years ago
0a435f0988
Merge remote-tracking branch 'origin/master'
3 years ago
0b94fc5033
Merge pull request #1324 from liamkerr/token_updates
...
Fixing Bugs with Token Counter
3 years ago
a1cde7e646
disabled SD model download after multiple complaints
3 years ago
6365a41f59
Update esrgan_model.py
...
Use alternate ESRGAN Model download path.
3 years ago
3ff0de2c59
added --disable-console-progressbars to disable progressbars in console
...
disabled printing prompts to console by default, enabled by --enable-console-prompts
3 years ago
4ec4af6e0b
add checkpoint info to saved embeddings
3 years ago
71fe7fa49f
fix using aaaa-100 embedding when the prompt has aaaa-10000 and you have both aaaa-100 and aaaa-10000 in the directory with embeddings.
3 years ago
88ec0cf557
fix for incorrect embedding token length calculation (will break seeds that use embeddings, you're welcome!)
...
add option to input initialization text for embeddings
3 years ago
6e063124ac
Merge pull request #1403 from d8ahazard/ScuNET
...
Add ScuNET Denoiser/Upscaler, Fix some Model Loader issues
3 years ago
a32a068ed1
Merge branch 'master' into token_updates
3 years ago
f34e2293d0
Merge remote-tracking branch 'origin/master'
3 years ago
0758f6e641
fix --ckpt option breaking model selection
3 years ago
a9d7eb722f
Merge branch 'master' into saving
3 years ago
7308aeefd9
Merge branch 'master' into token_updates
3 years ago
5d26ba2b4b
Merge branch 'master' into ScuNET
3 years ago
5f561ee95d
Merge remote-tracking branch 'origin/master'
3 years ago
0114057ad6
fix incorrect use of glob in modelloader for #1410
3 years ago
820f1dc96b
initial support for training textual inversion
3 years ago
32edf1732f
os.path.normpath wasn't working, reverting to manual strip
3 years ago
70f5267047
use os.path.normpath for better safety checking
3 years ago
3cf1a96006
added safety for blank directory naming patterns
3 years ago
2deea86781
Put reload buttons in row and add secondary style
3 years ago
07e40ad7f2
add custom script body only refresh option
3 years ago
cf33268d68
add script body only refresh
3 years ago
0aa354bd5e
remove styling from python side
3 years ago
027c5aae55
update reloading message style
3 years ago
6048002dad
Add scope warning to refresh button
3 years ago
afaa03c5fd
add redefinition guard to gradio_routes_templates_response
3 years ago
121ed7d36f
Add progress bar for SwinIR in cmd
...
I do not know how to add them to the UI...
3 years ago
4f8490cd56
add restart button
3 years ago
4c2478a68a
add script reload method
3 years ago
bc38c80cfc
add sampler_noise_scheduler_override switch
3 years ago
9de1e56e2d
add sampler_noise_scheduler_override property
3 years ago
bdaa36c844
When device is MPS, use CPU for GFPGAN instead
...
GFPGAN will not work if the device is MPS, so default to CPU instead.
3 years ago
3c6a049fc3
consolidated token counter functions
3 years ago
ff8dc1908a
fixed token counter for prompt editing
3 years ago
abdbf1de64
token counters now update when roll artist and style buttons are pressed https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/1194#issuecomment-1261203893
3 years ago
ad1fbbae93
Merge branch 'master' into fix-vram
3 years ago
d1db330010
ALT + return will submit prompt when it's in focus
3 years ago
8deae07700
Add ScuNET DeNoiser/Upscaler
...
Q&D Implementation of ScuNET, thanks to our handy model loader. :P
https://github.com/cszn/SCUNet
3 years ago
e82ea20299
Optimize model loader
...
Child classes only get populated to __subclassess__ when they are imported. We don't actually need to import any of them to webui any more, so clean up webUI imports and make sure loader imports children.
Also, fix command line paths not actually being passed to the scalers.
3 years ago
89f0acc6bf
remove extra print from BSRGAN
3 years ago
f253790b40
Merge pull request #1371 from d8ahazard/master
...
Fix LDSR, BSRGAN, recursive SD checkpoint Loading
3 years ago
3f64e23f81
fix model checkpoint merger tab failing to save model
3 years ago
a9a0320d26
Merge branch 'master' into master
3 years ago
2b03f0bbda
if --ckpt option is specified, load that model
3 years ago
7ab91d9e1b
Update bsrgan_model.py
3 years ago
3665551b12
Merge branch 'master' of https://github.com/d8ahazard/stable-diffusion-webui
3 years ago
8f1d412e7b
Fix BSRGAN Model loading.
3 years ago
2162be514a
Merge branch 'master' into master
3 years ago
3a876b16a9
Merge remote-tracking branch 'origin/master'
3 years ago
4794202ebc
hello #1109
3 years ago
ac21d308cd
fix for one error with BSRGAN, though it fails to work anyway #1109
3 years ago
43c87ef0fc
change default inpaint mode to original
3 years ago
9fc1e49bd2
Set default value for ckpt-dir
3 years ago
f71d02b85f
Remove unused LDSR opt
3 years ago
5d52231bcb
Logging....
...
Cleanup. Sorry.
3 years ago
ca87c09c0e
Fix recursive model loading
...
Ensure we find checkpoints within subdirectories.
3 years ago
19eb1467f1
Fix BSRGAN variable not found.
3 years ago
99aa132df7
Remove useless print message
3 years ago
8d60645106
Fix model paths, ensure we have the right files.
...
Also, clean up logging in the ldsr arch file.
3 years ago
64c6b13312
Remove LDSR project.yaml if too large.
...
If we accidentally downloaded the wrong file and saved it as project.yaml, this will delete it so it can be re-downloaded.
3 years ago
41f9449d96
Fix LDSR YAML path
3 years ago
980cd1697a
prevent neural network resizing when it is not necessary #1109
3 years ago
98cc6c6e74
add embeddings dir
3 years ago
5c0c778a65
fixed so that {prompt} can be anywhere in style
3 years ago
ff4df06c57
refined [styles] pattern and added [prompt_no_styles]
3 years ago
b60cd0809f
return the dropdown that mysteriously disappeared
3 years ago
9a54077d4d
repair broken highres fix #1109
3 years ago
cef838a6ab
revert the annotation not supported by old pythons
3 years ago
d1f098540a
remove unwanted formatting/functionality from the PR
3 years ago
2552204fcb
fix for broken codeformer in PR
3 years ago
aec811c5e6
undo upscaler model filename tampering
3 years ago
a5e7b371d6
fix the bug with broken rescaling in PR
3 years ago
8f1b315318
fix bugs in the PR
3 years ago
25414bcd05
Merge pull request #1109 from d8ahazard/ModelLoader
...
Model Loader, Fixes
3 years ago
f80c3696f6
fix the sys not found error when importing sd_samplers that appeared after PR
3 years ago
28307a9f10
force usage of cloned k-diffusion
3 years ago
ebd2c48115
return shortest checkpoint title match
3 years ago
642b7e333e
add get_closet_checkpoint_match
3 years ago
435fd2112a
Fixes, cleanup.
3 years ago
d73741794d
Merge remote-tracking branch 'upstream/master' into ModelLoader
3 years ago
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.
3 years ago
a112168d28
Save parameters as comments when saving as jpg
3 years ago
ca5901b5c8
Save should use desired sample format fixes #1028
3 years ago
c715ef04d1
fix for incorrect model weight loading for #814
3 years ago
965dcf4469
improve code quality
3 years ago
b05355770c
add new samplers
3 years ago
f28ce3e3a1
Merge branch 'master' into saving
3 years ago
be5555fce4
drop the print
3 years ago
e9919f2ab7
Sort scripts loading order
3 years ago
66fed8ffb8
Add custom name and try-except
3 years ago
819fd3af40
Add output folder icons
...
Changed the hidden element class name to a more generic one, so people can reuse it if they want to hide further elements in the future
3 years ago
02c4b757b6
Add output folder icons
...
Handling of the --hide-ui-dir-config flag and added multi-platform code for opening a folder
3 years ago
f8acbb8f88
Add output folder icons
...
Adds icons on the first 3 tabs to directly open the corresponding images output directory
3 years ago
4127f4aff8
fix program breaking on empty prompt
3 years ago
c1c27dad3b
new implementation for attention/emphasis
3 years ago
29ce8a687d
remove unneded debug print
3 years ago
c2d5b29040
Move silu to sd_hijack
3 years ago
c938679de7
Fix memory leak and reduce memory usage
3 years ago
041d2aefc0
Respect --ckpt-dir command-line argument when merging models ( #1261 )
...
* Update .gitignore to ignore *all* checkpoint files in /models
* Fixed typo in UI
3 years ago
7acfaca05a
update lists of models after merging them in checkpoints tab
...
support saving as half
3 years ago
791808c890
correctly list and display model names for #1261
3 years ago
leko
C43H66N12O12S2
brkirch
AUTOMATIC
Greendayle
Milly
Jairo Correa
DepFA
Raphael Stoeckli
xpscyho
Rae Fu
Justin Riddiough
dan
RnDMonkey
RnDMonkey
hentailord85ez
Hanusz Leszek
Lopyter
d8ahazard
liamkerr
Alexandre Simard
Liam
Trung Ngo
Justin Maier
WDevelopsWebApps
safentisAuth
Michoko
William Moorehouse