aboutsummaryrefslogtreecommitdiffstats
path: root/modules/shared.py
AgeCommit message (Collapse)AuthorLines
2022-09-29Holy $hit.d8ahazard-9/+9
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.
2022-09-29new implementation for attention/emphasisAUTOMATIC-1/+2
2022-09-29update lists of models after merging them in checkpoints tabAUTOMATIC-1/+1
support saving as half
2022-09-28added support for automatically installing latest k-diffusionAUTOMATIC-2/+3
added eta parameter to parameters output for generated images split eta settings into ancestral and ddim (because they have different default values)
2022-09-28save parameters for images when using the Save button.AUTOMATIC-1/+1
2022-09-28Update shared.pyC43H66N12O12S2-1/+1
2022-09-27Merge remote-tracking branch 'upstream/master' into ModelLoaderd8ahazard-1/+9
2022-09-27Use model loader with stable-diffusion too.d8ahazard-11/+17
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.
2022-09-27Fix downssample typo in optionsDave Bauman-1/+1
Updated `downssample` to `down-sample`, matching spelling in other places.
2022-09-27rename DDIM eta labelDepFA-2/+2
2022-09-27Add extra kdiffusion parametersDepFA-0/+3
2022-09-27Add options for exposed ddim sampler paramsDepFA-0/+4
ddim_eta & ddim_discretize
2022-09-27job_timestamp initialization changeDepFA-1/+2
2022-09-26Re-implement universal model loadingd8ahazard-4/+8
2022-09-25Changed job_id to timestampEyrie-5/+4
2022-09-25fix formattingEyrie-1/+1
2022-09-25fix formattingEyrie-0/+1
2022-09-25Added job_id pattern for directoriesEyrie-1/+5
2022-09-24Disable 'batch img2img' when launched with --hide-ui-dir-configEyeDeck-1/+1
Prevent writing to arbitrary directories, as usual
2022-09-24Fix to XY_Grid script console progress bar and other progress bar ↵RnDMonkey-0/+7
improvements (#890) Fix to XY_Grid script console progress bar and other progress bar improvements #890
2022-09-23Option to use advanced upscalers with normal img2imgAUTOMATIC-1/+1
2022-09-23prevent saving settings with bogus valuesAUTOMATIC-12/+11
2022-09-23Merge pull request #847 from rewbs/rewbs-optionally-save-before-color-correctionAUTOMATIC1111-0/+1
Add option to save before color correction. This helps with some posterisation issues in img2img loopback.
2022-09-23gfpgan: just download the damn modelAUTOMATIC-2/+1
2022-09-23add warning for when user's settings are brokenAUTOMATIC-0/+21
2022-09-23Merge from masterRobin Fernandes-73/+118
2022-09-22settings categories split to columns, remade categoriesAUTOMATIC-47/+61
2022-09-22emergency fix for the settings screen breaking the programAUTOMATIC-94/+103
2022-09-22Add Section keys and headers to settingsDepFA-31/+51
2022-09-22Fixed directory name generation process.Prof-Cheese-0/+1
'Max prompt words' has been added to config and modified to be used in the directory name generation process.
2022-09-22Add option to always log generation infoJohan Aires Rastén-0/+1
2022-09-22Add option to save before color correction. Add suffix param when saving ↵Robin Fernandes-0/+1
files, used for special saves without color correction and face restoration.
2022-09-22A big rework, just what you were secretly hoping for!AUTOMATIC-2/+1
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
2022-09-22reworking #775AUTOMATIC-11/+9
2022-09-22Basic settings for realesrgan model selection.d8ahazard-0/+5
I don't like that you have to restart the app, but it works.
2022-09-21Add LDSR and "GoLatent?" Upscaling (#763)d8ahazard-0/+6
* Add LDSR Upscaling
2022-09-21Merge remote-tracking branch 'origin/master'AUTOMATIC-2/+4
2022-09-21--opt-split-attention now on by default for torch.cuda, off for others (cpu ↵AUTOMATIC-5/+2
and MPS; because the option does not work there according to reports)
2022-09-21disallow no tiling as we don't support itC43H66N12O12S2-1/+1
2022-09-21breakout tile optionsC43H66N12O12S2-2/+4
2022-09-20Update shared.pyC43H66N12O12S2-2/+3
2022-09-20added --use-textbox-seed option to make long seeds possible from web uiAUTOMATIC-0/+2
2022-09-20Enable neural network upscalers for highres. fixAUTOMATIC-0/+1
2022-09-20Keep legacy behaviour wrt reuse of filename during batch processesolivier-1/+1
2022-09-20Support reusing filename stems during batch processing in Extras tabolivier-0/+1
2022-09-19avoid exception if emptyC43H66N12O12S2-1/+1
2022-09-19automatically match any version gfpganC43H66N12O12S2-2/+2
2022-09-19fix the issue with incorrect js options on page loadAUTOMATIC-0/+1
add a setting for lightbox max size images use setting for lightbox max size images late to let user change it and see results
2022-09-19fix grammerberkybear-1/+1
2022-09-19fix some typos and remove unused importberkybear-3/+2