820f1dc96b
initial support for training textual inversion
3 years ago
2b03f0bbda
if --ckpt option is specified, load that model
3 years ago
b60cd0809f
return the dropdown that mysteriously disappeared
3 years ago
d1f098540a
remove unwanted formatting/functionality from the PR
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
c1c27dad3b
new implementation for attention/emphasis
3 years ago
7acfaca05a
update lists of models after merging them in checkpoints tab
...
support saving as half
3 years ago
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)
3 years ago
aea5b2510e
save parameters for images when using the Save button.
3 years ago
047ca73388
Update shared.py
3 years ago
5756d517a6
Merge remote-tracking branch 'upstream/master' into ModelLoader
3 years ago
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.
3 years ago
c055132606
Fix downssample typo in options
...
Updated `downssample` to `down-sample`, matching spelling in other places.
3 years ago
61585e5778
rename DDIM eta label
3 years ago
6b78833e33
Add extra kdiffusion parameters
3 years ago
619668ccfe
Add options for exposed ddim sampler params
...
ddim_eta & ddim_discretize
3 years ago
16e7ac09df
job_timestamp initialization change
3 years ago
740070ea9c
Re-implement universal model loading
3 years ago
1877a3767e
Changed job_id to timestamp
3 years ago
4c3d4aad60
fix formatting
3 years ago
e13912dfde
fix formatting
3 years ago
40166dbf08
Added job_id pattern for directories
3 years ago
b5d705e263
Disable 'batch img2img' when launched with --hide-ui-dir-config
...
Prevent writing to arbitrary directories, as usual
3 years ago
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
3 years ago
1a0353675d
Option to use advanced upscalers with normal img2img
3 years ago
6fa20d51dc
prevent saving settings with bogus values
3 years ago
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.
3 years ago
d4205e66fa
gfpgan: just download the damn model
3 years ago
7ef361dfc3
add warning for when user's settings are broken
3 years ago
03738668c0
Merge from master
3 years ago
77cf346d93
settings categories split to columns, remade categories
3 years ago
75b90a5e40
emergency fix for the settings screen breaking the program
3 years ago
dec7584903
Add Section keys and headers to settings
3 years ago
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.
3 years ago
a213d3a21c
Add option to always log generation info
3 years ago
25eb1e3d90
Add option to save before color correction. Add suffix param when saving files, used for special saves without color correction and face restoration.
3 years ago
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
3 years ago
3eaae8ae65
reworking #775
3 years ago
c214c428bc
Basic settings for realesrgan model selection.
...
I don't like that you have to restart the app, but it works.
3 years ago
1a1f7e85c7
Add LDSR and "GoLatent?" Upscaling ( #763 )
...
* Add LDSR Upscaling
3 years ago
4b26b50df0
Merge remote-tracking branch 'origin/master'
3 years ago
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)
3 years ago
29d6084f47
disallow no tiling as we don't support it
3 years ago
403bb02948
breakout tile options
3 years ago
55dc847c48
Update shared.py
3 years ago
19a75d38d7
added --use-textbox-seed option to make long seeds possible from web ui
3 years ago
06cd206107
Enable neural network upscalers for highres. fix
3 years ago
06e076e48a
Keep legacy behaviour wrt reuse of filename during batch processes
3 years ago
5fe2c75da0
Support reusing filename stems during batch processing in Extras tab
3 years ago
AUTOMATIC
d8ahazard
C43H66N12O12S2
Dave Bauman
DepFA
Eyrie
EyeDeck
RnDMonkey
Robin Fernandes
Prof-Cheese
Johan Aires Rastén
olivier