Commit Graph

143 Commits

Author SHA1 Message Date
d8ahazard
5d26ba2b4b
Merge branch 'master' into ScuNET 2022-10-02 07:56:22 -05:00
AUTOMATIC
820f1dc96b initial support for training textual inversion 2022-10-02 15:03:39 +03:00
d8ahazard
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
AUTOMATIC
2b03f0bbda if --ckpt option is specified, load that model 2022-09-30 22:16:03 +03:00
AUTOMATIC
b60cd0809f return the dropdown that mysteriously disappeared 2022-09-30 12:56:36 +03:00
AUTOMATIC
d1f098540a remove unwanted formatting/functionality from the PR 2022-09-30 11:42:40 +03:00
d8ahazard
d73741794d Merge remote-tracking branch 'upstream/master' into ModelLoader 2022-09-29 19:59:36 -05:00
d8ahazard
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
AUTOMATIC
c1c27dad3b new implementation for attention/emphasis 2022-09-29 11:31:48 +03:00
AUTOMATIC
7acfaca05a update lists of models after merging them in checkpoints tab
support saving as half
2022-09-29 00:59:44 +03:00
AUTOMATIC
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
AUTOMATIC
aea5b2510e save parameters for images when using the Save button. 2022-09-28 17:05:23 +03:00
C43H66N12O12S2
047ca73388
Update shared.py 2022-09-28 05:11:40 +03:00
d8ahazard
5756d517a6 Merge remote-tracking branch 'upstream/master' into ModelLoader 2022-09-27 11:02:41 -05:00
d8ahazard
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
Dave Bauman
c055132606
Fix downssample typo in options
Updated `downssample` to `down-sample`, matching spelling in other places.
2022-09-27 09:50:06 -04:00
DepFA
61585e5778 rename DDIM eta label 2022-09-27 09:30:45 +03:00
DepFA
6b78833e33 Add extra kdiffusion parameters 2022-09-27 09:30:45 +03:00
DepFA
619668ccfe Add options for exposed ddim sampler params
ddim_eta & ddim_discretize
2022-09-27 09:30:45 +03:00
DepFA
16e7ac09df job_timestamp initialization change 2022-09-27 08:51:59 +03:00
d8ahazard
740070ea9c Re-implement universal model loading 2022-09-26 09:29:50 -05:00
Eyrie
1877a3767e Changed job_id to timestamp 2022-09-25 17:11:07 +03:00
Eyrie
4c3d4aad60 fix formatting 2022-09-25 17:11:07 +03:00
Eyrie
e13912dfde fix formatting 2022-09-25 17:11:07 +03:00
Eyrie
40166dbf08 Added job_id pattern for directories 2022-09-25 17:11:07 +03:00
EyeDeck
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
RnDMonkey
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
AUTOMATIC
1a0353675d Option to use advanced upscalers with normal img2img 2022-09-23 17:37:47 +03:00
AUTOMATIC
6fa20d51dc prevent saving settings with bogus values 2022-09-23 17:27:30 +03:00
AUTOMATIC1111
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
AUTOMATIC
d4205e66fa gfpgan: just download the damn model 2022-09-23 10:26:00 +03:00
AUTOMATIC
7ef361dfc3 add warning for when user's settings are broken 2022-09-23 09:15:00 +03:00
Robin Fernandes
03738668c0 Merge from master 2022-09-23 00:54:32 +00:00
AUTOMATIC
77cf346d93 settings categories split to columns, remade categories 2022-09-22 21:32:44 +03:00
AUTOMATIC
75b90a5e40 emergency fix for the settings screen breaking the program 2022-09-22 20:41:22 +03:00
DepFA
dec7584903 Add Section keys and headers to settings 2022-09-22 20:26:21 +03:00
Prof-Cheese
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
Johan Aires Rastén
a213d3a21c Add option to always log generation info 2022-09-22 16:34:54 +03:00
Robin Fernandes
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
AUTOMATIC
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
AUTOMATIC
3eaae8ae65 reworking #775 2022-09-22 07:59:27 +03:00
d8ahazard
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
d8ahazard
1a1f7e85c7
Add LDSR and "GoLatent?" Upscaling (#763)
* Add LDSR Upscaling
2022-09-21 16:06:37 +03:00
AUTOMATIC
4b26b50df0 Merge remote-tracking branch 'origin/master' 2022-09-21 09:49:07 +03:00
AUTOMATIC
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
C43H66N12O12S2
29d6084f47 disallow no tiling as we don't support it 2022-09-21 09:09:39 +03:00
C43H66N12O12S2
403bb02948 breakout tile options 2022-09-21 09:09:39 +03:00
C43H66N12O12S2
55dc847c48 Update shared.py 2022-09-20 23:31:06 +03:00
AUTOMATIC
19a75d38d7 added --use-textbox-seed option to make long seeds possible from web ui 2022-09-20 20:10:01 +03:00
AUTOMATIC
06cd206107 Enable neural network upscalers for highres. fix 2022-09-20 19:32:26 +03:00