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.
2022-10-02 19:56:37 +03:00
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
2022-10-02 19:40:51 +03:00
6e063124ac
Merge pull request #1403 from d8ahazard/ScuNET
...
Add ScuNET Denoiser/Upscaler, Fix some Model Loader issues
2022-10-02 17:39:34 +03:00
a32a068ed1
Merge branch 'master' into token_updates
2022-10-02 10:26:20 -04:00
f34e2293d0
Merge remote-tracking branch 'origin/master'
2022-10-02 17:25:28 +03:00
0758f6e641
fix --ckpt option breaking model selection
2022-10-02 17:24:50 +03:00
a9d7eb722f
Merge branch 'master' into saving
2022-10-02 17:03:01 +03:00
7308aeefd9
Merge branch 'master' into token_updates
2022-10-02 10:02:38 -04:00
5d26ba2b4b
Merge branch 'master' into ScuNET
2022-10-02 07:56:22 -05:00
5f561ee95d
Merge remote-tracking branch 'origin/master'
2022-10-02 15:49:59 +03:00
0114057ad6
fix incorrect use of glob in modelloader for #1410
2022-10-02 15:49:42 +03:00
820f1dc96b
initial support for training textual inversion
2022-10-02 15:03:39 +03:00
32edf1732f
os.path.normpath wasn't working, reverting to manual strip
2022-10-01 21:37:14 -07:00
70f5267047
use os.path.normpath for better safety checking
2022-10-01 21:18:15 -07:00
3cf1a96006
added safety for blank directory naming patterns
2022-10-01 21:11:03 -07:00
2deea86781
Put reload buttons in row and add secondary style
2022-10-02 01:36:30 +01:00
07e40ad7f2
add custom script body only refresh option
2022-10-02 01:19:55 +01:00
cf33268d68
add script body only refresh
2022-10-02 01:18:42 +01:00
0aa354bd5e
remove styling from python side
2022-10-02 00:13:47 +01:00
027c5aae55
update reloading message style
2022-10-01 23:29:26 +01:00
6048002dad
Add scope warning to refresh button
2022-10-01 23:10:07 +01:00
afaa03c5fd
add redefinition guard to gradio_routes_templates_response
2022-10-01 22:43:45 +01:00
121ed7d36f
Add progress bar for SwinIR in cmd
...
I do not know how to add them to the UI...
2022-10-01 14:04:20 -04:00
4f8490cd56
add restart button
2022-10-01 18:33:31 +01:00
4c2478a68a
add script reload method
2022-10-01 18:30:53 +01:00
bc38c80cfc
add sampler_noise_scheduler_override switch
2022-10-01 08:08:50 +03:00
9de1e56e2d
add sampler_noise_scheduler_override property
2022-10-01 08:08:50 +03:00
bdaa36c844
When device is MPS, use CPU for GFPGAN instead
...
GFPGAN will not work if the device is MPS, so default to CPU instead.
2022-09-30 23:53:25 -04:00
3c6a049fc3
consolidated token counter functions
2022-09-30 18:22:50 -04:00
ff8dc1908a
fixed token counter for prompt editing
2022-09-30 18:22:50 -04:00
abdbf1de64
token counters now update when roll artist and style buttons are pressed https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/1194#issuecomment-1261203893
2022-09-30 18:22:40 -04:00
d1db330010
ALT + return will submit prompt when it's in focus
2022-09-30 15:39:57 -05:00
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
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.
2022-09-30 15:26:18 -05:00
89f0acc6bf
remove extra print from BSRGAN
2022-09-30 23:18:47 +03:00
f253790b40
Merge pull request #1371 from d8ahazard/master
...
Fix LDSR, BSRGAN, recursive SD checkpoint Loading
2022-09-30 23:09:18 +03:00
3f64e23f81
fix model checkpoint merger tab failing to save model
2022-09-30 22:57:25 +03:00
a9a0320d26
Merge branch 'master' into master
2022-09-30 14:27:27 -05:00
2b03f0bbda
if --ckpt option is specified, load that model
2022-09-30 22:16:03 +03:00
7ab91d9e1b
Update bsrgan_model.py
2022-09-30 13:29:33 -05:00
3665551b12
Merge branch 'master' of https://github.com/d8ahazard/stable-diffusion-webui
2022-09-30 12:51:57 -05:00
8f1d412e7b
Fix BSRGAN Model loading.
2022-09-30 12:51:54 -05:00
2162be514a
Merge branch 'master' into master
2022-09-30 11:33:41 -05:00
3a876b16a9
Merge remote-tracking branch 'origin/master'
2022-09-30 18:56:23 +03:00
4794202ebc
hello #1109
2022-09-30 18:56:10 +03:00
ac21d308cd
fix for one error with BSRGAN, though it fails to work anyway #1109
2022-09-30 18:55:46 +03:00
43c87ef0fc
change default inpaint mode to original
2022-09-30 18:07:49 +03:00
9fc1e49bd2
Set default value for ckpt-dir
2022-09-30 09:38:57 -05:00
f71d02b85f
Remove unused LDSR opt
2022-09-30 09:29:31 -05:00
5d52231bcb
Logging....
...
Cleanup. Sorry.
2022-09-30 09:28:48 -05:00
ca87c09c0e
Fix recursive model loading
...
Ensure we find checkpoints within subdirectories.
2022-09-30 09:28:28 -05:00
19eb1467f1
Fix BSRGAN variable not found.
2022-09-30 09:05:00 -05:00
99aa132df7
Remove useless print message
2022-09-30 08:56:39 -05:00
8d60645106
Fix model paths, ensure we have the right files.
...
Also, clean up logging in the ldsr arch file.
2022-09-30 08:55:04 -05:00
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.
2022-09-30 08:41:25 -05:00
41f9449d96
Fix LDSR YAML path
2022-09-30 08:33:06 -05:00
980cd1697a
prevent neural network resizing when it is not necessary #1109
2022-09-30 14:23:41 +03:00
98cc6c6e74
add embeddings dir
2022-09-30 14:16:26 +03:00
5c0c778a65
fixed so that {prompt} can be anywhere in style
2022-09-30 13:00:43 +03:00
ff4df06c57
refined [styles] pattern and added [prompt_no_styles]
2022-09-30 13:00:43 +03:00
b60cd0809f
return the dropdown that mysteriously disappeared
2022-09-30 12:56:36 +03:00
9a54077d4d
repair broken highres fix #1109
2022-09-30 12:26:41 +03:00
cef838a6ab
revert the annotation not supported by old pythons
2022-09-30 12:15:29 +03:00
d1f098540a
remove unwanted formatting/functionality from the PR
2022-09-30 11:42:40 +03:00
2552204fcb
fix for broken codeformer in PR
2022-09-30 11:03:00 +03:00
aec811c5e6
undo upscaler model filename tampering
2022-09-30 10:52:45 +03:00
a5e7b371d6
fix the bug with broken rescaling in PR
2022-09-30 10:38:48 +03:00
8f1b315318
fix bugs in the PR
2022-09-30 09:46:52 +03:00
25414bcd05
Merge pull request #1109 from d8ahazard/ModelLoader
...
Model Loader, Fixes
2022-09-30 09:35:58 +03:00
f80c3696f6
fix the sys not found error when importing sd_samplers that appeared after PR
2022-09-30 08:21:05 +03:00
28307a9f10
force usage of cloned k-diffusion
2022-09-30 07:57:39 +03:00
ebd2c48115
return shortest checkpoint title match
2022-09-30 07:37:05 +03:00
642b7e333e
add get_closet_checkpoint_match
2022-09-30 07:37:05 +03:00
435fd2112a
Fixes, cleanup.
2022-09-29 19:59:53 -05:00
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
a112168d28
Save parameters as comments when saving as jpg
2022-09-29 19:07:29 +03:00
ca5901b5c8
Save should use desired sample format fixes #1028
2022-09-29 19:07:29 +03:00
c715ef04d1
fix for incorrect model weight loading for #814
2022-09-29 15:40:28 +03:00
965dcf4469
improve code quality
2022-09-29 13:52:51 +03:00
b05355770c
add new samplers
2022-09-29 13:52:51 +03:00
f28ce3e3a1
Merge branch 'master' into saving
2022-09-29 12:19:13 +02:00
be5555fce4
drop the print
2022-09-29 12:48:42 +03:00
e9919f2ab7
Sort scripts loading order
2022-09-29 12:48:42 +03:00
66fed8ffb8
Add custom name and try-except
2022-09-29 12:41:47 +03:00
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
2022-09-29 12:10:00 +03:00
02c4b757b6
Add output folder icons
...
Handling of the --hide-ui-dir-config flag and added multi-platform code for opening a folder
2022-09-29 12:10:00 +03:00
f8acbb8f88
Add output folder icons
...
Adds icons on the first 3 tabs to directly open the corresponding images output directory
2022-09-29 12:10:00 +03:00
4127f4aff8
fix program breaking on empty prompt
2022-09-29 11:39:55 +03:00
c1c27dad3b
new implementation for attention/emphasis
2022-09-29 11:31:48 +03:00
29ce8a687d
remove unneded debug print
2022-09-29 08:03:23 +03:00
041d2aefc0
Respect --ckpt-dir command-line argument when merging models ( #1261 )
...
* Update .gitignore to ignore *all* checkpoint files in /models
* Fixed typo in UI
2022-09-29 01:00:48 +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
791808c890
correctly list and display model names for #1261
2022-09-29 00:21:54 +03:00
d62954c2bc
fix broken DDIM with img2img
2022-09-28 22:30:52 +03:00
a703f56d73
clone k-diffusion instead of installing it via pip, and do not install its requirements.txt
2022-09-28 21:38:26 +03:00
278e7c7114
Merge pull request #1194 from liamkerr/token_count
...
Token count
2022-09-28 19:22:55 +03:00
1deac2b645
do nor add log messages to saved iamge parameters
2022-09-28 18:20:30 +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
9be0d1b89e
Merge remote-tracking branch 'origin/master'
2022-09-28 17:05:32 +03:00
AUTOMATIC