fluxdev/stable-diffusion-webui-forge

1## 1.7.02 3### Features:4* settings tab rework: add search field, add categories, split UI settings page into many5* add altdiffusion-m18 support ([#13364](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13364))6* support inference with LyCORIS GLora networks ([#13610](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13610))7* add lora-embedding bundle system ([#13568](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13568))8* option to move prompt from top row into generation parameters9* add support for SSD-1B ([#13865](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13865))10* support inference with OFT networks ([#13692](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13692))11* script metadata and DAG sorting mechanism ([#13944](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13944))12* support HyperTile optimization ([#13948](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13948))13* add support for SD 2.1 Turbo ([#14170](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14170))14* remove Train->Preprocessing tab and put all its functionality into Extras tab15* initial IPEX support for Intel Arc GPU ([#14171](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14171))16 17### Minor:18* allow reading model hash from images in img2img batch mode ([#12767](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12767))19* add option to align with sgm repo's sampling implementation ([#12818](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12818))20* extra field for lora metadata viewer: `ss_output_name` ([#12838](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12838))21* add action in settings page to calculate all SD checkpoint hashes ([#12909](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12909))22* add button to copy prompt to style editor ([#12975](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12975))23* add --skip-load-model-at-start option ([#13253](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13253))24* write infotext to gif images25* read infotext from gif images ([#13068](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13068))26* allow configuring the initial state of InputAccordion in ui-config.json ([#13189](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13189))27* allow editing whitespace delimiters for ctrl+up/ctrl+down prompt editing ([#13444](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13444))28* prevent accidentally closing popup dialogs ([#13480](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13480))29* added option to play notification sound or not ([#13631](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13631))30* show the preview image in the full screen image viewer if available ([#13459](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13459))31* support for webui.settings.bat ([#13638](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13638))32* add an option to not print stack traces on ctrl+c33* start/restart generation by Ctrl (Alt) + Enter ([#13644](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13644))34* update prompts_from_file script to allow concatenating entries with the general prompt ([#13733](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13733))35* added a visible checkbox to input accordion36* added an option to hide all txt2img/img2img parameters in an accordion ([#13826](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13826))37* added 'Path' sorting option for Extra network cards ([#13968](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13968))38* enable prompt hotkeys in style editor ([#13931](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13931))39* option to show batch img2img results in UI ([#14009](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14009))40* infotext updates: add option to disregard certain infotext fields, add option to not include VAE in infotext, add explanation to infotext settings page, move some options to infotext settings page41* add FP32 fallback support on sd_vae_approx ([#14046](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14046))42* support XYZ scripts / split hires path from unet ([#14126](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14126))43* allow use of mutiple styles csv files ([#14125](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14125))44 45### Extensions and API:46* update gradio to 3.41.247* support installed extensions list api ([#12774](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12774))48* update pnginfo API to return dict with parsed values49* add noisy latent to `ExtraNoiseParams` for callback ([#12856](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12856))50* show extension datetime in UTC ([#12864](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12864), [#12865](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12865), [#13281](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13281))51* add an option to choose how to combine hires fix and refiner52* include program version in info response. ([#13135](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13135))53* sd_unet support for SDXL54* patch DDPM.register_betas so that users can put given_betas in model yaml ([#13276](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13276))55* xyz_grid: add prepare ([#13266](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13266))56* allow multiple localization files with same language in extensions ([#13077](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13077))57* add onEdit function for js and rework token-counter.js to use it58* fix the key error exception when processing override_settings keys ([#13567](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13567))59* ability for extensions to return custom data via api in response.images ([#13463](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13463))60* call state.jobnext() before postproces*() ([#13762](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13762))61* add option to set notification sound volume ([#13884](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13884))62* update Ruff to 0.1.6 ([#14059](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14059))63* add Block component creation callback ([#14119](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14119))64* catch uncaught exception with ui creation scripts ([#14120](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14120))65* use extension name for determining an extension is installed in the index ([#14063](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14063))66* update is_installed() from launch_utils.py to fix reinstalling already installed packages ([#14192](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14192))67 68### Bug Fixes:69* fix pix2pix producing bad results70* fix defaults settings page breaking when any of main UI tabs are hidden71* fix error that causes some extra networks to be disabled if both <lora:> and <lyco:> are present in the prompt72* fix for Reload UI function: if you reload UI on one tab, other opened tabs will no longer stop working73* prevent duplicate resize handler ([#12795](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12795))74* small typo: vae resolve bug ([#12797](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12797))75* hide broken image crop tool ([#12792](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12792))76* don't show hidden samplers in dropdown for XYZ script ([#12780](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12780))77* fix style editing dialog breaking if it's opened in both img2img and txt2img tabs78* hide --gradio-auth and --api-auth values from /internal/sysinfo report79* add missing infotext for RNG in options ([#12819](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12819))80* fix notification not playing when built-in webui tab is inactive ([#12834](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12834))81* honor `--skip-install` for extension installers ([#12832](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12832))82* don't print blank stdout in extension installers ([#12833](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12833), [#12855](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12855))83* get progressbar to display correctly in extensions tab84* keep order in list of checkpoints when loading model that doesn't have a checksum85* fix inpainting models in txt2img creating black pictures86* fix generation params regex ([#12876](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12876))87* fix batch img2img output dir with script ([#12926](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12926))88* fix #13080 - Hypernetwork/TI preview generation ([#13084](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13084))89* fix bug with sigma min/max overrides. ([#12995](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12995))90* more accurate check for enabling cuDNN benchmark on 16XX cards ([#12924](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12924))91* don't use multicond parser for negative prompt counter ([#13118](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13118))92* fix data-sort-name containing spaces ([#13412](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13412))93* update card on correct tab when editing metadata ([#13411](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13411))94* fix viewing/editing metadata when filename contains an apostrophe ([#13395](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13395))95* fix: --sd_model in "Prompts from file or textbox" script is not working ([#13302](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13302))96* better Support for Portable Git ([#13231](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13231))97* fix issues when webui_dir is not work_dir ([#13210](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13210))98* fix: lora-bias-backup don't reset cache ([#13178](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13178))99* account for customizable extra network separators whyen removing extra network text from the prompt ([#12877](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12877))100* re fix batch img2img output dir with script ([#13170](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13170))101* fix `--ckpt-dir` path separator and option use `short name` for checkpoint dropdown ([#13139](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13139))102* consolidated allowed preview formats, Fix extra network `.gif` not woking as preview ([#13121](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13121))103* fix venv_dir=- environment variable not working as expected on linux ([#13469](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13469))104* repair unload sd checkpoint button105* edit-attention fixes ([#13533](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13533))106* fix bug when using --gfpgan-models-path ([#13718](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13718))107* properly apply sort order for extra network cards when selected from dropdown108* fixes generation restart not working for some users when 'Ctrl+Enter' is pressed ([#13962](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13962))109* thread safe extra network list_items ([#13014](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13014))110* fix not able to exit metadata popup when pop up is too big ([#14156](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14156))111* fix auto focal point crop for opencv >= 4.8 ([#14121](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14121))112* make 'use-cpu all' actually apply to 'all' ([#14131](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14131))113* extras tab batch: actually use original filename114* make webui not crash when running with --disable-all-extensions option115 116### Other:117* non-local condition ([#12814](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12814))118* fix minor typos ([#12827](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12827))119* remove xformers Python version check ([#12842](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12842))120* style: file-metadata word-break ([#12837](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12837))121* revert SGM noise multiplier change for img2img because it breaks hires fix122* do not change quicksettings dropdown option when value returned is `None` ([#12854](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12854))123* [RC 1.6.0 - zoom is partly hidden] Update style.css ([#12839](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12839))124* chore: change extension time format ([#12851](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12851))125* WEBUI.SH - Use torch 2.1.0 release candidate for Navi 3 ([#12929](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12929))126* add Fallback at images.read_info_from_image if exif data was invalid ([#13028](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13028))127* update cmd arg description ([#12986](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12986))128* fix: update shared.opts.data when add_option ([#12957](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12957), [#13213](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13213))129* restore missing tooltips ([#12976](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12976))130* use default dropdown padding on mobile ([#12880](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12880))131* put enable console prompts option into settings from commandline args ([#13119](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13119))132* fix some deprecated types ([#12846](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12846))133* bump to torchsde==0.2.6 ([#13418](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13418))134* update dragdrop.js ([#13372](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13372))135* use orderdict as lru cache:opt/bug ([#13313](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13313))136* XYZ if not include sub grids do not save sub grid ([#13282](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13282))137* initialize state.time_start befroe state.job_count ([#13229](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13229))138* fix fieldname regex ([#13458](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13458))139* change denoising_strength default to None. ([#13466](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13466))140* fix regression ([#13475](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13475))141* fix IndexError ([#13630](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13630))142* fix: checkpoints_loaded:{checkpoint:state_dict}, model.load_state_dict issue in dict value empty ([#13535](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13535))143* update bug_report.yml ([#12991](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12991))144* requirements_versions httpx==0.24.1 ([#13839](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13839))145* fix parenthesis auto selection ([#13829](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13829))146* fix #13796 ([#13797](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13797))147* corrected a typo in `modules/cmd_args.py` ([#13855](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13855))148* feat: fix randn found element of type float at pos 2 ([#14004](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14004))149* adds tqdm handler to logging_config.py for progress bar integration ([#13996](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13996))150* hotfix: call shared.state.end() after postprocessing done ([#13977](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13977))151* fix dependency address patch 1 ([#13929](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13929))152* save sysinfo as .json ([#14035](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14035))153* move exception_records related methods to errors.py ([#14084](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14084))154* compatibility ([#13936](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13936))155* json.dump(ensure_ascii=False) ([#14108](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14108))156* dir buttons start with / so only the correct dir will be shown and no… ([#13957](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13957))157* alternate implementation for unet forward replacement that does not depend on hijack being applied158* re-add `keyedit_delimiters_whitespace` setting lost as part of commit e294e46 ([#14178](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14178))159* fix `save_samples` being checked early when saving masked composite ([#14177](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14177))160* slight optimization for mask and mask_composite ([#14181](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14181))161* add import_hook hack to work around basicsr/torchvision incompatibility ([#14186](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14186))162 163## 1.6.1164 165### Bug Fixes:166 * fix an error causing the webui to fail to start ([#13839](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13839))167 168## 1.6.0169 170### Features:171 * refiner support [#12371](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12371)172 * add NV option for Random number generator source setting, which allows to generate same pictures on CPU/AMD/Mac as on NVidia videocards173 * add style editor dialog174 * hires fix: add an option to use a different checkpoint for second pass ([#12181](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12181))175 * option to keep multiple loaded models in memory ([#12227](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12227))176 * new samplers: Restart, DPM++ 2M SDE Exponential, DPM++ 2M SDE Heun, DPM++ 2M SDE Heun Karras, DPM++ 2M SDE Heun Exponential, DPM++ 3M SDE, DPM++ 3M SDE Karras, DPM++ 3M SDE Exponential ([#12300](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12300), [#12519](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12519), [#12542](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12542))177 * rework DDIM, PLMS, UniPC to use CFG denoiser same as in k-diffusion samplers:178   * makes all of them work with img2img179   * makes prompt composition posssible (AND)180   * makes them available for SDXL181 * always show extra networks tabs in the UI ([#11808](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/11808))182 * 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))183 * textual inversion inference support for SDXL184 * extra networks UI: show metadata for SD checkpoints185 * checkpoint merger: add metadata support 186 * 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))187 * VAE: allow selecting own VAE for each checkpoint (in user metadata editor)188 * VAE: add selected VAE to infotext189 * 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))190 * 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))191 * 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 it192 * 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))193 * add `--medvram-sdxl` flag that only enables `--medvram` for SDXL models194 * 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))195 196### Minor:197 * img2img batch: RAM savings, VRAM savings, .tif, .tiff in img2img batch ([#12120](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12120), [#12514](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12514), [#12515](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12515))198 * postprocessing/extras: RAM savings ([#12479](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12479))199 * XYZ: in the axis labels, remove pathnames from model filenames200 * XYZ: support hires sampler ([#12298](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12298))201 * XYZ: new option: use text inputs instead of dropdowns ([#12491](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12491))202 * add gradio version warning203 * sort list of VAE checkpoints ([#12297](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12297))204 * 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))205 * move some settings to their own section: img2img, VAE206 * add checkbox to show/hide dirs for extra networks207 * Add TAESD(or more) options for all the VAE encode/decode operation ([#12311](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12311))208 * 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))209 * sampler fixes/tweaks: s_tmax, s_churn, s_noise, s_tmax ([#12354](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12354), [#12356](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12356), [#12357](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12357), [#12358](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12358), [#12375](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12375), [#12521](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12521))210 * update README.md with correct instructions for Linux installation ([#12352](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12352))211 * option to not save incomplete images, on by default ([#12338](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12338))212 * enable cond cache by default213 * git autofix for repos that are corrupted ([#12230](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12230))214 * allow to open images in new browser tab by middle mouse button ([#12379](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12379))215 * automatically open webui in browser when running "locally" ([#12254](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12254))216 * put commonly used samplers on top, make DPM++ 2M Karras the default choice217 * 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))218 * option to cache Lora networks in memory219 * rework hires fix UI to use accordion220 * face restoration and tiling moved to settings - use "Options in main UI" setting if you want them back221 * change quicksettings items to have variable width222 * Lora: add Norm module, add support for bias ([#12503](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12503))223 * Lora: output warnings in UI rather than fail for unfitting loras; switch to logging for error output in console224 * support search and display of hashes for all extra network items ([#12510](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12510))225 * add extra noise param for img2img operations ([#12564](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12564))226 * support for Lora with bias ([#12584](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12584))227 * make interrupt quicker ([#12634](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12634))228 * configurable gallery height ([#12648](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12648))229 * make results column sticky ([#12645](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12645))230 * more hash filename patterns ([#12639](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12639))231 * make image viewer actually fit the whole page ([#12635](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12635))232 * make progress bar work independently from live preview display which results in it being updated a lot more often233 * forbid Full live preview method for medvram and add a setting to undo the forbidding234 * make it possible to localize tooltips and placeholders235 * add option to align with sgm repo's sampling implementation ([#12818](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12818))236 * Restore faces and Tiling generation parameters have been moved to settings out of main UI237   * if you want to put them back into main UI, use `Options in main UI` setting on the UI page.238 239### Extensions and API:240 * gradio 3.41.2241 * also bump versions for packages: transformers, GitPython, accelerate, scikit-image, timm, tomesd242 * support tooltip kwarg for gradio elements: gr.Textbox(label='hello', tooltip='world')243 * properly clear the total console progressbar when using txt2img and img2img from API244 * add cmd_arg --disable-extra-extensions and --disable-all-extensions ([#12294](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12294))245 * shared.py and webui.py split into many files246 * add --loglevel commandline argument for logging247 * add a custom UI element that combines accordion and checkbox248 * avoid importing gradio in tests because it spams warnings249 * put infotext label for setting into OptionInfo definition rather than in a separate list250 * make `StableDiffusionProcessingImg2Img.mask_blur` a property, make more inline with PIL `GaussianBlur` ([#12470](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12470))251 * option to make scripts UI without gr.Group252 * add a way for scripts to register a callback for before/after just a single component's creation253 * use dataclass for StableDiffusionProcessing254 * store patches for Lora in a specialized module instead of inside torch255 * 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))256 * add extra noise callback ([#12616](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12616))257 * dump current stack traces when exiting with SIGINT258 * add type annotations for extra fields of shared.sd_model259 260### Bug Fixes:261 * Don't crash if out of local storage quota for javascriot localStorage262 * XYZ plot do not fail if an exception occurs263 * fix missing TI hash in infotext if generation uses both negative and positive TI ([#12269](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12269))264 * localization fixes ([#12307](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12307))265 * fix sdxl model invalid configuration after the hijack266 * correctly toggle extras checkbox for infotext paste ([#12304](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12304))267 * open raw sysinfo link in new page ([#12318](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12318))268 * prompt parser: Account for empty field in alternating words syntax ([#12319](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12319))269 * add tab and carriage return to invalid filename chars ([#12327](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12327))270 * fix api only Lora not working ([#12387](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12387))271 * fix options in main UI misbehaving when there's just one element272 * make it possible to use a sampler from infotext even if it's hidden in the dropdown273 * fix styles missing from the prompt in infotext when making a grid of batch of multiplie images274 * prevent bogus progress output in console when calculating hires fix dimensions275 * fix --use-textbox-seed276 * fix broken `Lora/Networks: use old method` option ([#12466](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12466))277 * properly return `None` for VAE hash when using `--no-hashing` ([#12463](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12463))278 * MPS/macOS fixes and optimizations ([#12526](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12526))279 * add second_order to samplers that mistakenly didn't have it280 * when refreshing cards in extra networks UI, do not discard user's custom resolution281 * 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))282 * fix inpaint upload for alpha masks ([#12588](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12588))283 * fix exception when image sizes are not integers ([#12586](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12586))284 * fix incorrect TAESD Latent scale ([#12596](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12596))285 * auto add data-dir to gradio-allowed-path ([#12603](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12603))286 * fix exception if extensuions dir is missing ([#12607](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12607))287 * fix issues with api model-refresh and vae-refresh ([#12638](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12638))288 * fix img2img background color for transparent images option not being used ([#12633](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12633))289 * attempt to resolve NaN issue with unstable VAEs in fp32 mk2 ([#12630](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12630))290 * implement missing undo hijack for SDXL291 * fix xyz swap axes ([#12684](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12684))292 * fix errors in backup/restore tab if any of config files are broken ([#12689](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12689))293 * fix SD VAE switch error after model reuse ([#12685](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12685))294 * fix trying to create images too large for the chosen format ([#12667](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12667))295 * create Gradio temp directory if necessary ([#12717](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12717))296 * prevent possible cache loss if exiting as it's being written by using an atomic operation to replace the cache with the new version297 * set devices.dtype_unet correctly298 * run RealESRGAN on GPU for non-CUDA devices ([#12737](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12737))299 * prevent extra network buttons being obscured by description for very small card sizes ([#12745](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12745))300 * fix error that causes some extra networks to be disabled if both <lora:> and <lyco:> are present in the prompt301 * fix defaults settings page breaking when any of main UI tabs are hidden302 * fix incorrect save/display of new values in Defaults page in settings303 * fix for Reload UI function: if you reload UI on one tab, other opened tabs will no longer stop working304 * fix an error that prevents VAE being reloaded after an option change if a VAE near the checkpoint exists ([#12797](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12737))305 * hide broken image crop tool ([#12792](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12737))306 * don't show hidden samplers in dropdown for XYZ script ([#12780](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12737))307 * fix style editing dialog breaking if it's opened in both img2img and txt2img tabs308 * fix a bug allowing users to bypass gradio and API authentication (reported by vysecurity) 309 * fix notification not playing when built-in webui tab is inactive ([#12834](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12834))310 * honor `--skip-install` for extension installers ([#12832](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12832))311 * don't print blank stdout in extension installers ([#12833](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12832), [#12855](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12855))312 * do not change quicksettings dropdown option when value returned is `None` ([#12854](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12854))313 * get progressbar to display correctly in extensions tab314 315 316## 1.5.2317 318### Bug Fixes:319 * fix memory leak when generation fails320 * update doggettx cross attention optimization to not use an unreasonable amount of memory in some edge cases -- suggestion by MorkTheOrk321 322 323## 1.5.1324 325### Minor:326 * support parsing text encoder blocks in some new LoRAs327 * delete scale checker script due to user demand328 329### Extensions and API:330 * add postprocess_batch_list script callback331 332### Bug Fixes:333 * fix TI training for SD1334 * fix reload altclip model error335 * prepend the pythonpath instead of overriding it336 * fix typo in SD_WEBUI_RESTARTING337 * if txt2img/img2img raises an exception, finally call state.end()338 * fix composable diffusion weight parsing339 * restyle Startup profile for black users340 * fix webui not launching with --nowebui341 * catch exception for non git extensions342 * fix some options missing from /sdapi/v1/options343 * fix for extension update status always saying "unknown"344 * fix display of extra network cards that have `<>` in the name345 * update lora extension to work with python 3.8346 347 348## 1.5.0349 350### Features:351 * SD XL support352 * user metadata system for custom networks353 * extended Lora metadata editor: set activation text, default weight, view tags, training info354 * Lora extension rework to include other types of networks (all that were previously handled by LyCORIS extension)355 * show github stars for extenstions356 * img2img batch mode can read extra stuff from png info357 * img2img batch works with subdirectories358 * hotkeys to move prompt elements: alt+left/right359 * restyle time taken/VRAM display360 * add textual inversion hashes to infotext361 * optimization: cache git extension repo information362 * move generate button next to the generated picture for mobile clients363 * hide cards for networks of incompatible Stable Diffusion version in Lora extra networks interface364 * skip installing packages with pip if they all are already installed - startup speedup of about 2 seconds365 366### Minor:367 * checkbox to check/uncheck all extensions in the Installed tab368 * add gradio user to infotext and to filename patterns369 * allow gif for extra network previews370 * add options to change colors in grid371 * use natural sort for items in extra networks372 * Mac: use empty_cache() from torch 2 to clear VRAM373 * added automatic support for installing the right libraries for Navi3 (AMD)374 * add option SWIN_torch_compile to accelerate SwinIR upscale375 * suppress printing TI embedding info at start to console by default376 * speedup extra networks listing377 * added `[none]` filename token.378 * removed thumbs extra networks view mode (use settings tab to change width/height/scale to get thumbs)379 * add always_discard_next_to_last_sigma option to XYZ plot380 * automatically switch to 32-bit float VAE if the generated picture has NaNs without the need for `--no-half-vae` commandline flag.381 382### Extensions and API:383 * api endpoints: /sdapi/v1/server-kill, /sdapi/v1/server-restart, /sdapi/v1/server-stop384 * allow Script to have custom metaclass385 * add model exists status check /sdapi/v1/options386 * rename --add-stop-route to --api-server-stop387 * add `before_hr` script callback388 * add callback `after_extra_networks_activate`389 * disable rich exception output in console for API by default, use WEBUI_RICH_EXCEPTIONS env var to enable390 * return http 404 when thumb file not found391 * allow replacing extensions index with environment variable392 393### Bug Fixes:394 * fix for catch errors when retrieving extension index #11290395 * fix very slow loading speed of .safetensors files when reading from network drives396 * API cache cleanup397 * fix UnicodeEncodeError when writing to file CLIP Interrogator batch mode398 * fix warning of 'has_mps' deprecated from PyTorch399 * fix problem with extra network saving images as previews losing generation info400 * fix throwing exception when trying to resize image with I;16 mode401 * fix for #11534: canvas zoom and pan extension hijacking shortcut keys402 * fixed launch script to be runnable from any directory403 * don't add "Seed Resize: -1x-1" to API image metadata404 * correctly remove end parenthesis with ctrl+up/down405 * fixing --subpath on newer gradio version406 * fix: check fill size none zero when resize  (fixes #11425)407 * use submit and blur for quick settings textbox408 * save img2img batch with images.save_image()409 * prevent running preload.py for disabled extensions410 * fix: previously, model name was added together with directory name to infotext and to [model_name] filename pattern; directory name is now not included411 412 413## 1.4.1414 415### Bug Fixes:416 * add queue lock for refresh-checkpoints417 418## 1.4.0419 420### Features:421 * zoom controls for inpainting422 * run basic torch calculation at startup in parallel to reduce the performance impact of first generation423 * option to pad prompt/neg prompt to be same length424 * remove taming_transformers dependency425 * custom k-diffusion scheduler settings426 * add an option to show selected settings in main txt2img/img2img UI427 * sysinfo tab in settings428 * infer styles from prompts when pasting params into the UI429 * an option to control the behavior of the above430 431### Minor:432 * bump Gradio to 3.32.0433 * bump xformers to 0.0.20434 * Add option to disable token counters435 * tooltip fixes & optimizations436 * make it possible to configure filename for the zip download437 * `[vae_filename]` pattern for filenames438 * Revert discarding penultimate sigma for DPM-Solver++(2M) SDE439 * change UI reorder setting to multiselect440 * read version info form CHANGELOG.md if git version info is not available441 * link footer API to Wiki when API is not active442 * persistent conds cache (opt-in optimization)443 444### Extensions:445 * After installing extensions, webui properly restarts the process rather than reloads the UI 446 * Added VAE listing to web API. Via: /sdapi/v1/sd-vae447 * custom unet support448 * Add onAfterUiUpdate callback449 * refactor EmbeddingDatabase.register_embedding() to allow unregistering450 * add before_process callback for scripts451 * add ability for alwayson scripts to specify section and let user reorder those sections452 453### Bug Fixes:454 * Fix dragging text to prompt455 * fix incorrect quoting for infotext values with colon in them456 * fix "hires. fix" prompt sharing same labels with txt2img_prompt457 * Fix s_min_uncond default type int458 * Fix for #10643 (Inpainting mask sometimes not working)459 * fix bad styling for thumbs view in extra networks #10639460 * fix for empty list of optimizations #10605461 * small fixes to prepare_tcmalloc for Debian/Ubuntu compatibility462 * fix --ui-debug-mode exit463 * patch GitPython to not use leaky persistent processes464 * fix duplicate Cross attention optimization after UI reload465 * torch.cuda.is_available() check for SdOptimizationXformers466 * fix hires fix using wrong conds in second pass if using Loras.467 * handle exception when parsing generation parameters from png info468 * fix upcast attention dtype error469 * forcing Torch Version to 1.13.1 for RX 5000 series GPUs470 * split mask blur into X and Y components, patch Outpainting MK2 accordingly471 * don't die when a LoRA is a broken symlink472 * allow activation of Generate Forever during generation473 474 475## 1.3.2476 477### Bug Fixes:478 * fix files served out of tmp directory even if they are saved to disk479 * fix postprocessing overwriting parameters480 481## 1.3.1482 483### Features:484 * revert default cross attention optimization to Doggettx485 486### Bug Fixes:487 * fix bug: LoRA don't apply on dropdown list sd_lora488 * fix png info always added even if setting is not enabled489 * fix some fields not applying in xyz plot490 * fix "hires. fix" prompt sharing same labels with txt2img_prompt491 * fix lora hashes not being added properly to infotex if there is only one lora492 * fix --use-cpu failing to work properly at startup493 * make --disable-opt-split-attention command line option work again494 495## 1.3.0496 497### Features:498 * add UI to edit defaults499 * token merging (via dbolya/tomesd)500 * settings tab rework: add a lot of additional explanations and links501 * load extensions' Git metadata in parallel to loading the main program to save a ton of time during startup502 * update extensions table: show branch, show date in separate column, and show version from tags if available503 * TAESD - another option for cheap live previews504 * allow choosing sampler and prompts for second pass of hires fix - hidden by default, enabled in settings505 * calculate hashes for Lora506 * add lora hashes to infotext507 * when pasting infotext, use infotext's lora hashes to find local loras for `<lora:xxx:1>` entries whose hashes match loras the user has508 * select cross attention optimization from UI509 510### Minor:511 * bump Gradio to 3.31.0512 * bump PyTorch to 2.0.1 for macOS and Linux AMD513 * allow setting defaults for elements in extensions' tabs514 * allow selecting file type for live previews515 * show "Loading..." for extra networks when displaying for the first time516 * suppress ENSD infotext for samplers that don't use it517 * clientside optimizations518 * add options to show/hide hidden files and dirs in extra networks, and to not list models/files in hidden directories519 * allow whitespace in styles.csv520 * add option to reorder tabs521 * move some functionality (swap resolution and set seed to -1) to client522 * option to specify editor height for img2img523 * button to copy image resolution into img2img width/height sliders524 * switch from pyngrok to ngrok-py525 * lazy-load images in extra networks UI526 * set "Navigate image viewer with gamepad" option to false by default, by request527 * change upscalers to download models into user-specified directory (from commandline args) rather than the default models/<...>528 * allow hiding buttons in ui-config.json529 530### Extensions:531 * add /sdapi/v1/script-info api532 * use Ruff to lint Python code533 * use ESlint to lint Javascript code534 * add/modify CFG callbacks for Self-Attention Guidance extension535 * add command and endpoint for graceful server stopping536 * add some locals (prompts/seeds/etc) from processing function into the Processing class as fields537 * rework quoting for infotext items that have commas in them to use JSON (should be backwards compatible except for cases where it didn't work previously)538 * add /sdapi/v1/refresh-loras api checkpoint post request539 * tests overhaul540 541### Bug Fixes:542 * fix an issue preventing the program from starting if the user specifies a bad Gradio theme543 * fix broken prompts from file script544 * fix symlink scanning for extra networks545 * fix --data-dir ignored when launching via webui-user.bat COMMANDLINE_ARGS546 * allow web UI to be ran fully offline547 * fix inability to run with --freeze-settings548 * fix inability to merge checkpoint without adding metadata549 * fix extra networks' save preview image not adding infotext for jpeg/webm550 * remove blinking effect from text in hires fix and scale resolution preview551 * make links to `http://<...>.git` extensions work in the extension tab552 * fix bug with webui hanging at startup due to hanging git process553 554 555## 1.2.1556 557### Features:558 * add an option to always refer to LoRA by filenames559 560### Bug Fixes:561 * never refer to LoRA by an alias if multiple LoRAs have same alias or the alias is called none562 * fix upscalers disappearing after the user reloads UI563 * allow bf16 in safe unpickler (resolves problems with loading some LoRAs)564 * allow web UI to be ran fully offline565 * fix localizations not working566 * fix error for LoRAs: `'LatentDiffusion' object has no attribute 'lora_layer_mapping'`567 568## 1.2.0569 570### Features:571 * do not wait for Stable Diffusion model to load at startup572 * add filename patterns: `[denoising]`573 * directory hiding for extra networks: dirs starting with `.` will hide their cards on extra network tabs unless specifically searched for574 * LoRA: for the `<...>` text in prompt, use name of LoRA that is in the metdata of the file, if present, instead of filename (both can be used to activate LoRA)575 * LoRA: read infotext params from kohya-ss's extension parameters if they are present and if his extension is not active576 * LoRA: fix some LoRAs not working (ones that have 3x3 convolution layer)577 * LoRA: add an option to use old method of applying LoRAs (producing same results as with kohya-ss)578 * add version to infotext, footer and console output when starting579 * add links to wiki for filename pattern settings580 * add extended info for quicksettings setting and use multiselect input instead of a text field581 582### Minor:583 * bump Gradio to 3.29.0584 * bump PyTorch to 2.0.1585 * `--subpath` option for gradio for use with reverse proxy586 * Linux/macOS: use existing virtualenv if already active (the VIRTUAL_ENV environment variable)587 * do not apply localizations if there are none (possible frontend optimization)588 * add extra `None` option for VAE in XYZ plot589 * print error to console when batch processing in img2img fails590 * create HTML for extra network pages only on demand591 * allow directories starting with `.` to still list their models for LoRA, checkpoints, etc592 * put infotext options into their own category in settings tab593 * do not show licenses page when user selects Show all pages in settings594 595### Extensions:596 * tooltip localization support597 * add API method to get LoRA models with prompt598 599### Bug Fixes:600 * re-add `/docs` endpoint601 * fix gamepad navigation602 * make the lightbox fullscreen image function properly603 * fix squished thumbnails in extras tab604 * keep "search" filter for extra networks when user refreshes the tab (previously it showed everthing after you refreshed)605 * fix webui showing the same image if you configure the generation to always save results into same file606 * fix bug with upscalers not working properly607 * fix MPS on PyTorch 2.0.1, Intel Macs608 * make it so that custom context menu from contextMenu.js only disappears after user's click, ignoring non-user click events609 * prevent Reload UI button/link from reloading the page when it's not yet ready610 * fix prompts from file script failing to read contents from a drag/drop file611 612 613## 1.1.1614### Bug Fixes:615 * fix an error that prevents running webui on PyTorch<2.0 without --disable-safe-unpickle616 617## 1.1.0618### Features:619 * switch to PyTorch 2.0.0 (except for AMD GPUs)620 * visual improvements to custom code scripts621 * add filename patterns: `[clip_skip]`, `[hasprompt<>]`, `[batch_number]`, `[generation_number]`622 * add support for saving init images in img2img, and record their hashes in infotext for reproducability623 * automatically select current word when adjusting weight with ctrl+up/down624 * add dropdowns for X/Y/Z plot625 * add setting: Stable Diffusion/Random number generator source: makes it possible to make images generated from a given manual seed consistent across different GPUs626 * support Gradio's theme API627 * use TCMalloc on Linux by default; possible fix for memory leaks628 * add optimization option to remove negative conditioning at low sigma values #9177629 * embed model merge metadata in .safetensors file630 * extension settings backup/restore feature #9169631 * add "resize by" and "resize to" tabs to img2img632 * add option "keep original size" to textual inversion images preprocess633 * image viewer scrolling via analog stick634 * button to restore the progress from session lost / tab reload635 636### Minor:637 * bump Gradio to 3.28.1638 * change "scale to" to sliders in Extras tab639 * add labels to tool buttons to make it possible to hide them640 * add tiled inference support for ScuNET641 * add branch support for extension installation642 * change Linux installation script to install into current directory rather than `/home/username`643 * sort textual inversion embeddings by name (case-insensitive)644 * allow styles.csv to be symlinked or mounted in docker645 * remove the "do not add watermark to images" option646 * make selected tab configurable with UI config647 * make the extra networks UI fixed height and scrollable648 * add `disable_tls_verify` arg for use with self-signed certs649 650### Extensions:651 * add reload callback652 * add `is_hr_pass` field for processing653 654### Bug Fixes:655 * fix broken batch image processing on 'Extras/Batch Process' tab656 * add "None" option to extra networks dropdowns657 * fix FileExistsError for CLIP Interrogator658 * fix /sdapi/v1/txt2img endpoint not working on Linux #9319659 * fix disappearing live previews and progressbar during slow tasks660 * fix fullscreen image view not working properly in some cases661 * prevent alwayson_scripts args param resizing script_arg list when they are inserted in it662 * fix prompt schedule for second order samplers663 * fix image mask/composite for weird resolutions #9628664 * use correct images for previews when using AND (see #9491)665 * one broken image in img2img batch won't stop all processing666 * fix image orientation bug in train/preprocess667 * fix Ngrok recreating tunnels every reload668 * fix `--realesrgan-models-path` and `--ldsr-models-path` not working669 * fix `--skip-install` not working670 * use SAMPLE file format in Outpainting Mk2 & Poorman671 * do not fail all LoRAs if some have failed to load when making a picture672 673## 1.0.0674  * everything675