* hires fix: add an option to use a different checkpoint for second pass ([#12181](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12181))
* option to keep multiple loaded models in memory ([#12227](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12227))
* rework DDIM, PLMS, UniPC to use CFG denoiser same as in k-diffusion samplers:
* makes all of them work with img2img
* makes prompt composition posssible (AND)
* makes them available for SDXL
* always show extra networks tabs in the UI
* use less RAM when creating models
* always show extra networks tabs in the UI ([#11808](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/11808))
* use less RAM when creating models ([#11958](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/11958))
* textual inversion inference support for SDXL
* extra networks UI: show metadata for SD checkpoints
* checkpoint merger: add metadata support
* prompt editing and attention: add support for whitespace after the number ([ red : green : 0.5 ]) (seed breaking change)
* prompt editing and attention: add support for whitespace after the number ([ red : green : 0.5 ]) (seed breaking change) ([#12177](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12177))
* VAE: allow selecting own VAE for each checkpoint (in user metadata editor)
* VAE: add selected VAE to infotext
* options in main UI: add own separate setting for txt2img and img2img, correctly read values from pasted infotext, add setting for column count
* options in main UI: add own separate setting for txt2img and img2img, correctly read values from pasted infotext, add setting for column count ([#12551](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12551))
* XYZ: in the axis labels, remove pathnames from model filenames
* XYZ: support hires sampler
* XYZ: new option: use text inputs instead of dropdowns
* XYZ: support hires sampler ([#12298](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12298))
* XYZ: new option: use text inputs instead of dropdowns ([#12491](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12491))
* add gradio version warning
* sort list of VAE checkpoints
* use transparent white for mask in inpainting, along with an option to select the color
* sort list of VAE checkpoints ([#12297](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12297))
* use transparent white for mask in inpainting, along with an option to select the color ([#12326](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12326))
* move some settings to their own section: img2img, VAE
* add checkbox to show/hide dirs for extra networks
* Add TAESD(or more) options for all the VAE encode/decode operation
* gradio theme cache, new gradio themes, along with explanation that the user can input his own values
* update README.md with correct instructions for Linux installation
* option to not save incomplete images, on by default
* Add TAESD(or more) options for all the VAE encode/decode operation ([#12311](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12311))
* gradio theme cache, new gradio themes, along with explanation that the user can input his own values ([#12346](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12346), [#12355](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12355))
* update README.md with correct instructions for Linux installation ([#12352](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12352))
* option to not save incomplete images, on by default ([#12338](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12338))
* enable cond cache by default
* git autofix for repos that are corrupted
* allow to open images in new browser tab by middle mouse button
* automatically open webui in browser when running "locally"
* git autofix for repos that are corrupted ([#12230](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12230))
* allow to open images in new browser tab by middle mouse button ([#12379](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12379))
* automatically open webui in browser when running "locally" ([#12254](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12254))
* put commonly used samplers on top, make DPM++ 2M Karras the default choice
* zoom and pan: option to auto-expand a wide image
* zoom and pan: option to auto-expand a wide image ([#12413](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12413))
* option to cache Lora networks in memory
* rework hires fix UI to use accordion
* face restoration and tiling moved to settings - use "Options in main UI" setting if you want them back
* change quicksettings items to have variable width
* Lora: add Norm module, add support for bias
* Lora: add Norm module, add support for bias ([#12503](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12503))
* Lora: output warnings in UI rather than fail for unfitting loras; switch to logging for error output in console
* support search and display of hashes for all extra network items
* Add extra noise param for img2img operations
* support search and display of hashes for all extra network items ([#12510](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12510))
* Add extra noise param for img2img operations ([#12564](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12564))
### Extensions and API:
* gradio 3.39
* also bump versions for packages: transformers, GitPython, accelerate, scikit-image, timm, tomesd
* support tooltip kwarg for gradio elements: gr.Textbox(label='hello', tooltip='world')
* properly clear the total console progressbar when using txt2img and img2img from API
* add cmd_arg --disable-extensions all extra
* add cmd_arg --disable-extensions all extra ([#12294](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12294))
* shared.py and webui.py split into many files
* add --loglevel commandline argument for logging
* add a custom UI element that combines accordion and checkbox
* avoid importing gradio in tests because it spams warnings
* put infotext label for setting into OptionInfo definition rather than in a separate list
* make `StableDiffusionProcessingImg2Img.mask_blur` a property, make more inline with PIL `GaussianBlur`
* make `StableDiffusionProcessingImg2Img.mask_blur` a property, make more inline with PIL `GaussianBlur` ([#12470](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12470))
* option to make scripts UI without gr.Group
* add a way for scripts to register a callback for before/after just a single component's creation
* use dataclass for StableDiffusionProcessing
@@ -74,25 +74,25 @@
* fix memory leak when generation fails
* XYZ plot do not fail if an exception occurs
* update doggettx cross attention optimization to not use an unreasonable amount of memory in some edge cases -- suggestion by MorkTheOrk
* fix missing TI hash in infotext if generation uses both negative and positive TI
* localization fixes
* fix missing TI hash in infotext if generation uses both negative and positive TI ([#12269](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12269))
* fix sdxl model invalid configuration after the hijack
* correctly toggle extras checkbox for infotext paste
* open raw sysinfo link in new page
* prompt parser: Account for empty field in alternating words syntax
* add tab and carriage return to invalid filename chars
* fix api only Lora not working
* correctly toggle extras checkbox for infotext paste ([#12304](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12304))
* open raw sysinfo link in new page ([#12318](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12318))
* prompt parser: Account for empty field in alternating words syntax ([#12319](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12319))
* add tab and carriage return to invalid filename chars ([#12327](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12327))
* fix api only Lora not working ([#12387](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12387))
* fix options in main UI misbehaving when there's just one element
* make it possible to use a sampler from infotext even if it's hidden in the dropdown
* fix styles missing from the prompt in infotext when making a grid of batch of multiplie images
* prevent bogus progress output in console when calculating hires fix dimensions
* fix --use-textbox-seed
* fix broken `Lora/Networks: use old method` option
* properly return `None` for VAE hash when using `--no-hashing`
* MPS/macOS fixes and optimizations
* fix broken `Lora/Networks: use old method` option ([#12466](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12466))
* properly return `None` for VAE hash when using `--no-hashing` ([#12463](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12463))
* MPS/macOS fixes and optimizations ([#12526](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12526))
* add second_order to samplers that mistakenly didn't have it
* when refreshing cards in extra networks UI, do not discard user's custom resolution
* fix processing error that happens if batch_size is not a multiple of how many prompts/negative prompts there are #12509
* fix processing error that happens if batch_size is not a multiple of how many prompts/negative prompts there are ([#12509](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12509))
