stable-diffusion-webui/CHANGELOG.md

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

195 lines
9.7 KiB
Markdown
Raw Normal View History

2023-05-31 20:08:31 +00:00
## 1.3.1
2023-06-01 05:13:09 +00:00
### Features:
* revert default cross attention optimization to Doggettx
2023-05-31 20:08:31 +00:00
### Bug Fixes:
* fix bug: LoRA don't apply on dropdown list sd_lora
* fix png info always added even if setting is not enabled
* fix some fields not applying in xyz plot
* fix "hires. fix" prompt sharing same labels with txt2img_prompt
* fix lora hashes not being added properly to infotex if there is only one lora
2023-06-01 04:29:52 +00:00
* fix --use-cpu failing to work properly at startup
2023-06-01 05:13:09 +00:00
* make --disable-opt-split-attention command line option work again
2023-05-31 20:08:31 +00:00
## 1.3.0
2023-05-18 21:01:52 +00:00
### Features:
* add UI to edit defaults
* token merging (via dbolya/tomesd)
* settings tab rework: add a lot of additional explanations and links
2023-05-19 05:26:50 +00:00
* load extensions' Git metadata in parallel to loading the main program to save a ton of time during startup
2023-05-18 21:01:52 +00:00
* update extensions table: show branch, show date in separate column, and show version from tags if available
* TAESD - another option for cheap live previews
* allow choosing sampler and prompts for second pass of hires fix - hidden by default, enabled in settings
2023-05-21 14:36:40 +00:00
* calculate hashes for Lora
* add lora hashes to infotext
* when pasting infotext, use infotext's lora hashes to find local loras for `<lora:xxx:1>` entries whose hashes match loras the user has
* select cross attention optimization from UI
2023-05-18 21:01:52 +00:00
### Minor:
2023-05-19 05:26:50 +00:00
* bump Gradio to 3.31.0
* bump PyTorch to 2.0.1 for macOS and Linux AMD
2023-05-18 21:01:52 +00:00
* allow setting defaults for elements in extensions' tabs
* allow selecting file type for live previews
2023-05-19 05:26:50 +00:00
* show "Loading..." for extra networks when displaying for the first time
2023-05-18 21:01:52 +00:00
* suppress ENSD infotext for samplers that don't use it
* clientside optimizations
* add options to show/hide hidden files and dirs in extra networks, and to not list models/files in hidden directories
* allow whitespace in styles.csv
* add option to reorder tabs
* move some functionality (swap resolution and set seed to -1) to client
* option to specify editor height for img2img
* button to copy image resolution into img2img width/height sliders
* switch from pyngrok to ngrok-py
* lazy-load images in extra networks UI
* set "Navigate image viewer with gamepad" option to false by default, by request
2023-05-21 14:36:40 +00:00
* change upscalers to download models into user-specified directory (from commandline args) rather than the default models/<...>
* allow hiding buttons in ui-config.json
2023-05-18 21:01:52 +00:00
### Extensions:
* add /sdapi/v1/script-info api
2023-05-19 05:26:50 +00:00
* use Ruff to lint Python code
* use ESlint to lint Javascript code
* add/modify CFG callbacks for Self-Attention Guidance extension
* add command and endpoint for graceful server stopping
2023-05-18 21:01:52 +00:00
* add some locals (prompts/seeds/etc) from processing function into the Processing class as fields
2023-05-19 05:26:50 +00:00
* 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)
2023-05-21 14:36:40 +00:00
* add /sdapi/v1/refresh-loras api checkpoint post request
* tests overhaul
2023-05-18 21:01:52 +00:00
### Bug Fixes:
2023-05-19 05:26:50 +00:00
* fix an issue preventing the program from starting if the user specifies a bad Gradio theme
2023-05-18 21:01:52 +00:00
* fix broken prompts from file script
* fix symlink scanning for extra networks
* fix --data-dir ignored when launching via webui-user.bat COMMANDLINE_ARGS
* allow web UI to be ran fully offline
* fix inability to run with --freeze-settings
* fix inability to merge checkpoint without adding metadata
2023-05-19 05:26:50 +00:00
* fix extra networks' save preview image not adding infotext for jpeg/webm
2023-05-18 21:01:52 +00:00
* remove blinking effect from text in hires fix and scale resolution preview
2023-05-21 14:36:40 +00:00
* make links to `http://<...>.git` extensions work in the extension tab
* fix bug with webui hanging at startup due to hanging git process
2023-05-18 21:01:52 +00:00
2023-05-14 10:34:50 +00:00
## 1.2.1
2023-05-13 17:24:48 +00:00
### Features:
2023-05-19 05:26:50 +00:00
* add an option to always refer to LoRA by filenames
2023-05-13 17:24:48 +00:00
### Bug Fixes:
2023-05-19 05:26:50 +00:00
* never refer to LoRA by an alias if multiple LoRAs have same alias or the alias is called none
2023-05-13 17:24:48 +00:00
* fix upscalers disappearing after the user reloads UI
2023-05-19 05:26:50 +00:00
* allow bf16 in safe unpickler (resolves problems with loading some LoRAs)
2023-05-13 17:24:48 +00:00
* allow web UI to be ran fully offline
2023-05-13 17:47:32 +00:00
* fix localizations not working
2023-05-19 05:26:50 +00:00
* fix error for LoRAs: `'LatentDiffusion' object has no attribute 'lora_layer_mapping'`
2023-05-13 17:24:48 +00:00
2023-05-13 05:16:20 +00:00
## 1.2.0
2023-05-08 09:45:22 +00:00
### Features:
2023-05-19 05:26:50 +00:00
* do not wait for Stable Diffusion model to load at startup
* add filename patterns: `[denoising]`
* directory hiding for extra networks: dirs starting with `.` will hide their cards on extra network tabs unless specifically searched for
* 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)
* LoRA: read infotext params from kohya-ss's extension parameters if they are present and if his extension is not active
* LoRA: fix some LoRAs not working (ones that have 3x3 convolution layer)
* LoRA: add an option to use old method of applying LoRAs (producing same results as with kohya-ss)
2023-05-09 19:42:02 +00:00
* add version to infotext, footer and console output when starting
* add links to wiki for filename pattern settings
* add extended info for quicksettings setting and use multiselect input instead of a text field
2023-05-08 09:45:22 +00:00
### Minor:
2023-05-19 05:26:50 +00:00
* bump Gradio to 3.29.0
* bump PyTorch to 2.0.1
* `--subpath` option for gradio for use with reverse proxy
* Linux/macOS: use existing virtualenv if already active (the VIRTUAL_ENV environment variable)
* do not apply localizations if there are none (possible frontend optimization)
* add extra `None` option for VAE in XYZ plot
2023-05-08 09:45:22 +00:00
* print error to console when batch processing in img2img fails
* create HTML for extra network pages only on demand
2023-05-19 05:26:50 +00:00
* allow directories starting with `.` to still list their models for LoRA, checkpoints, etc
2023-05-09 19:42:02 +00:00
* put infotext options into their own category in settings tab
* do not show licenses page when user selects Show all pages in settings
2023-05-08 09:45:22 +00:00
### Extensions:
2023-05-19 05:26:50 +00:00
* tooltip localization support
* add API method to get LoRA models with prompt
2023-05-08 09:45:22 +00:00
### Bug Fixes:
2023-05-19 05:26:50 +00:00
* re-add `/docs` endpoint
2023-05-08 09:45:22 +00:00
* fix gamepad navigation
* make the lightbox fullscreen image function properly
* fix squished thumbnails in extras tab
* keep "search" filter for extra networks when user refreshes the tab (previously it showed everthing after you refreshed)
* fix webui showing the same image if you configure the generation to always save results into same file
2023-05-09 19:42:02 +00:00
* fix bug with upscalers not working properly
2023-05-19 05:26:50 +00:00
* fix MPS on PyTorch 2.0.1, Intel Macs
2023-05-09 19:42:02 +00:00
* make it so that custom context menu from contextMenu.js only disappears after user's click, ignoring non-user click events
* prevent Reload UI button/link from reloading the page when it's not yet ready
2023-05-11 11:49:14 +00:00
* fix prompts from file script failing to read contents from a drag/drop file
2023-05-08 09:45:22 +00:00
## 1.1.1
### Bug Fixes:
2023-05-19 05:26:50 +00:00
* fix an error that prevents running webui on PyTorch<2.0 without --disable-safe-unpickle
2023-05-01 11:33:44 +00:00
## 1.1.0
2023-04-29 19:50:34 +00:00
### Features:
2023-05-19 05:26:50 +00:00
* switch to PyTorch 2.0.0 (except for AMD GPUs)
2023-04-29 19:50:34 +00:00
* visual improvements to custom code scripts
2023-05-19 05:26:50 +00:00
* add filename patterns: `[clip_skip]`, `[hasprompt<>]`, `[batch_number]`, `[generation_number]`
2023-04-29 19:50:34 +00:00
* add support for saving init images in img2img, and record their hashes in infotext for reproducability
* automatically select current word when adjusting weight with ctrl+up/down
* add dropdowns for X/Y/Z plot
2023-05-19 05:26:50 +00:00
* add setting: Stable Diffusion/Random number generator source: makes it possible to make images generated from a given manual seed consistent across different GPUs
2023-04-29 19:50:34 +00:00
* support Gradio's theme API
* use TCMalloc on Linux by default; possible fix for memory leaks
2023-05-19 05:26:50 +00:00
* add optimization option to remove negative conditioning at low sigma values #9177
2023-04-29 19:50:34 +00:00
* embed model merge metadata in .safetensors file
* extension settings backup/restore feature #9169
* add "resize by" and "resize to" tabs to img2img
* add option "keep original size" to textual inversion images preprocess
* image viewer scrolling via analog stick
* button to restore the progress from session lost / tab reload
### Minor:
2023-05-19 05:26:50 +00:00
* bump Gradio to 3.28.1
* change "scale to" to sliders in Extras tab
2023-04-29 19:50:34 +00:00
* add labels to tool buttons to make it possible to hide them
* add tiled inference support for ScuNET
* add branch support for extension installation
2023-05-19 05:26:50 +00:00
* change Linux installation script to install into current directory rather than `/home/username`
* sort textual inversion embeddings by name (case-insensitive)
2023-04-29 19:50:34 +00:00
* allow styles.csv to be symlinked or mounted in docker
* remove the "do not add watermark to images" option
* make selected tab configurable with UI config
2023-05-19 05:26:50 +00:00
* make the extra networks UI fixed height and scrollable
* add `disable_tls_verify` arg for use with self-signed certs
2023-04-29 19:50:34 +00:00
### Extensions:
2023-05-19 05:26:50 +00:00
* add reload callback
* add `is_hr_pass` field for processing
2023-04-29 19:50:34 +00:00
### Bug Fixes:
* fix broken batch image processing on 'Extras/Batch Process' tab
* add "None" option to extra networks dropdowns
* fix FileExistsError for CLIP Interrogator
* fix /sdapi/v1/txt2img endpoint not working on Linux #9319
* fix disappearing live previews and progressbar during slow tasks
* fix fullscreen image view not working properly in some cases
* prevent alwayson_scripts args param resizing script_arg list when they are inserted in it
* fix prompt schedule for second order samplers
* fix image mask/composite for weird resolutions #9628
* use correct images for previews when using AND (see #9491)
* one broken image in img2img batch won't stop all processing
* fix image orientation bug in train/preprocess
* fix Ngrok recreating tunnels every reload
2023-05-19 05:26:50 +00:00
* fix `--realesrgan-models-path` and `--ldsr-models-path` not working
* fix `--skip-install` not working
* use SAMPLE file format in Outpainting Mk2 & Poorman
* do not fail all LoRAs if some have failed to load when making a picture
2023-04-29 19:50:34 +00:00
2023-05-01 11:33:44 +00:00
## 1.0.0
2023-04-29 19:50:34 +00:00
* everything