~/Projects/stable-diffusion-webui
git clone https://code.lsong.org/stable-diffusion-webui
Commit
- Commit
- 215466282635972a59b9f094e7a64b81711b11a3
- Author
- catboxanon <122327233+[email protected]>
- Date
- 2023-08-15 03:23:44 -0400 -0400
- Diffstat
CHANGELOG.md | 77 ++++++++++++++++++++++++++++++-----------------------
Add PR refs to changelog
diff --git a/CHANGELOG.md b/CHANGELOG.md index 6eae6a4feebdfb7d29e31d504b5c4828d621466f..e5986ed7df0edfc7be3646b1c59560917f1ad4a3 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,84 +1,94 @@ ## 1.6.0 ### Features: - * refiner support + * refiner support [#12371](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12371) * add NV option for Random number generator source setting, which allows to generate same pictures on CPU/AMD/Mac as on NVidia videocards * add style editor dialog +### Features: * hires fix: add an option to use a different checkpoint for second pass +## 1.6.0 - * option to keep multiple loaded models in memory + * option to keep multiple loaded models in memory ([#12227](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12227)) - * 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 + * 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)) * 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 -## 1.6.0 + * update README.md with correct instructions for Linux installation * refiner support -## 1.6.0 + * update README.md with correct instructions for Linux installation * add NV option for Random number generator source setting, which allows to generate same pictures on CPU/AMD/Mac as on NVidia videocards * 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)) ### Minor: - * img2img batch: RAM savings, VRAM savings, .tif, .tiff in img2img batch + * 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)) - * postprocessing/extras: RAM savings + * postprocessing/extras: RAM savings ([#12479](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12479)) * XYZ: in the axis labels, remove pathnames from model filenames - * XYZ: support hires sampler + * XYZ: support hires sampler ([#12298](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12298)) - +### Features: * option to keep multiple loaded models in memory +## 1.6.0 * add gradio version warning ### Features: + * make it possible to use a sampler from infotext even if it's hidden in the dropdown ### Features: -## 1.6.0 + * fix styles missing from the prompt in infotext when making a grid of batch of multiplie images * move some settings to their own section: img2img, VAE * add checkbox to show/hide dirs for extra networks ### Features: + * option to keep multiple loaded models in memory * refiner support ### Features: + * option to keep multiple loaded models in memory * add NV option for Random number generator source setting, which allows to generate same pictures on CPU/AMD/Mac as on NVidia videocards ### Features: + * option to keep multiple loaded models in memory * add style editor dialog ### Features: + * option to keep multiple loaded models in memory * hires fix: add an option to use a different checkpoint for second pass ### Features: + * option to keep multiple loaded models in memory * option to keep multiple loaded models in memory * enable cond cache by default - * refiner support + * git autofix for repos that are corrupted ([#12230](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12230)) + * enable cond cache by default - * refiner support + * enable cond cache by default ## 1.6.0 * refiner support - +### Features: - * refiner support ### Features: - * zoom and pan: option to auto-expand a wide image +## 1.5.1 * 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 - * refiner support +### Features: * 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 +### Features: * 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 + * support search and display of hashes for all extra network items ([#12510](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12510)) + * enable cond cache by default * add NV option for Random number generator source setting, which allows to generate same pictures on CPU/AMD/Mac as on NVidia videocards - ### 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 @@ -87,28 +98,29 @@ * Don't crash if out of local storage quota for javascriot localStorage * 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 - * hires fix: add an option to use a different checkpoint for second pass ### Features: + * prepend the pythonpath instead of overriding it - * localization fixes + * localization fixes ([#12307](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12307)) * fix sdxl model invalid configuration after the hijack - * correctly toggle extras checkbox for infotext paste + * correctly toggle extras checkbox for infotext paste ([#12304](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12304)) - * open raw sysinfo link in new page + * 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 + * 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 + * add tab and carriage return to invalid filename chars ([#12327](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12327)) - * option to keep multiple loaded models in memory + * refiner support + * refiner support * 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 - * option to keep multiple loaded models in memory + * fix broken `Lora/Networks: use old method` option ([#12466](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12466)) + * git autofix for repos that are corrupted * add style editor dialog - * option to keep multiple loaded models in memory + * git autofix for repos that are corrupted * hires fix: add an option to use a different checkpoint for second pass - * MPS/macOS fixes and optimizations * 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)) ## 1.5.1