* 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))
* use less RAM when creating models ([#11958](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/11958), [#12599](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12599))
* textual inversion inference support for SDXL
* extra networks UI: show metadata for SD checkpoints
* checkpoint merger: add metadata support
...
...
@@ -20,7 +20,11 @@
* 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 ([#12551](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12551))
* add resize handle to txt2img and img2img tabs, allowing to change the amount of horizontable space given to generation parameters and resulting image gallery ([#12687](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12687), [#12723](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12723))
* change default behavior for batching cond/uncond -- now it's on by default, and is disabled by an UI setting (Optimizatios -> Batch cond/uncond) - if you are on lowvram/medvram and are getting OOM exceptions, you will need to enable it
* show current position in queue and make it so that requests are processed in the order of arrival ([#12707](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12707))
* add `--medvram-sdxl` flag that only enables `--medvram` for SDXL models
* prompt editing timeline has separate range for first pass and hires-fix pass (seed breaking change) ([#12457](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12457))
* 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 ([#12413](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12413))
* zoom and pan: option to auto-expand a wide image, improved integration ([#12413](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12413), [#12727](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12727))
* 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
...
...
@@ -51,7 +55,16 @@
* 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 ([#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))
* add extra noise param for img2img operations ([#12564](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12564))
* support for Lora with bias ([#12584](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12584))
* make interrupt quicker ([#12634](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12634))
* make results column sticky ([#12645](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12645))
* more hash filename patterns ([#12639](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12639))
* make image viewer actually fit the whole page ([#12635](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12635))
* make progress bar work independently from live preview display which results in it being updated a lot more often
* forbid Full live preview method for medvram and add a setting to undo the forbidding
* make it possible to localize tooltips and placeholders
### Extensions and API:
* gradio 3.39
...
...
@@ -68,6 +81,11 @@
* 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
* store patches for Lora in a specialized module instead of inside torch
* support http/https URLs in API ([#12663](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12663), [#12698](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12698))
* add extra noise callback ([#12616](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12616))
* dump current stack traces when exiting with SIGINT
* add type annotations for extra fields of shared.sd_model
### Bug Fixes:
* Don't crash if out of local storage quota for javascriot localStorage
...
...
@@ -93,6 +111,24 @@
* 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](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12509))
* fix inpaint upload for alpha masks ([#12588](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12588))
* fix exception when image sizes are not integers ([#12586](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12586))
* auto add data-dir to gradio-allowed-path ([#12603](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12603))
* fix exception if extensuions dir is missing ([#12607](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12607))
* fix issues with api model-refresh and vae-refresh ([#12638](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12638))
* fix img2img background color for transparent images option not being used ([#12633](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12633))
* attempt to resolve NaN issue with unstable VAEs in fp32 mk2 ([#12630](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12630))
* fix errors in backup/restore tab if any of config files are broken ([#12689](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12689))
* fix SD VAE switch error after model reuse ([#12685](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12685))
* fix trying to create images too large for the chosen format ([#12667](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12667))
* create Gradio temp directory if necessary ([#12717](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12717))
* prevent possible cache loss if exiting as it's being written by using an atomic operation to replace the cache with the new version
* set devices.dtype_unet correctly
* run RealESRGAN on GPU for non-CUDA devices ([#12737](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12737))
* prevent extra network buttons being obscured by description for very small card sizes ([#12745](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12745))
