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.

support saving as half

added eta parameter to parameters output for generated images
split eta settings into ancestral and ddim (because they have different default values)

- Provides a better user experience
- Better suited to variable list of options
- Keep the UI "stable" as list contract or expand

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.

Updated `downssample` to `down-sample`, matching spelling in other places.

ddim_eta & ddim_discretize

Prevent writing to arbitrary directories, as usual

 Fix to XY_Grid script console progress bar and other progress bar improvements #890 

'Max prompt words' has been added to config and modified to be used in the directory name generation process.

Add option to save before color correction. Add suffix param when saving files, used for special saves without color correction and face restoration.

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

I don't like that you have to restart the app, but it works.

* Add LDSR Upscaling

--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)