aboutsummaryrefslogtreecommitdiffstats
path: root/modules/shared.py
Commit message (Collapse)AuthorAgeFilesLines
* Interrogate: add option to include ranks in outputGreg Fuller2022-10-121-0/+1
| | | | | | | | | | | | | | | | Since the UI also allows users to specify ranks, it can be useful to show people what ranks are being returned by interrogate This can also give much better results when feeding the interrogate results back into either img2img or txt2img, especially when trying to generate a specific character or scene for which you have a similar concept image Testing Steps: Launch Webui with command line arg: --deepdanbooru Navigate to img2img tab, use interrogate DeepBooru, verify tags appears as before. Use "Interrogate CLIP", verify prompt appears as before Navigate to Settings tab, enable new option, click "apply settings" Navigate to img2img, Interrogate DeepBooru again, verify that weights appear and are properly formatted. Note that "Interrogate CLIP" prompt is still unchanged In my testing, this change has no effect to "Interrogate CLIP", as it seems to generate a sentence-structured caption, and not a set of tags. (reproduce changes from https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/2149/commits/6ed4faac46c45ca7353f228aca9b436bbaba7bc7)
* add an option to unload models during hypernetwork training to save VRAMAUTOMATIC2022-10-111-0/+4
|
* Add cross-attention optimization from InvokeAIbrkirch2022-10-111-2/+3
| | | | | | * Add cross-attention optimization from InvokeAI (~30% speed improvement on MPS) * Add command line option for it * Make it default when CUDA is unavailable
* rename hypernetwork dir to hypernetworks to prevent clash with an old ↵AUTOMATIC2022-10-111-1/+1
| | | | filename that people who use zip instead of git clone will have
* Cleaned ngrok integrationJamnedZ2022-10-111-0/+1
|
* fixes related to mergeAUTOMATIC2022-10-111-2/+11
|
* Comma backtrack padding (#2192)hentailord85ez2022-10-111-0/+1
| | | Comma backtrack padding
* Added slider for deepbooru score threshold in settingsKenneth2022-10-111-0/+1
|
* add an option to not add watermark to created imagesAUTOMATIC2022-10-101-0/+1
|
* Merge pull request #2131 from ssysm/upstream-masterAUTOMATIC11112022-10-101-0/+1
|\ | | | | Add VAE Path Arguments
| * Merge branch 'master' of ↵ssysm2022-10-101-9/+11
| |\ | | | | | | | | | https://github.com/AUTOMATIC1111/stable-diffusion-webui into upstream-master
| * | add vae path argsssysm2022-10-101-1/+1
| | |
* | | add eta noise seed delta optionAUTOMATIC2022-10-101-0/+1
| | |
* | | --no-half-vaeAUTOMATIC2022-10-101-0/+1
| |/ |/|
* | Corrected CLIP Layer Ignore description and updated its range to the max ↵Fampai2022-10-091-1/+1
| | | | | | | | possible
* | show model selection setting on top of pageAUTOMATIC2022-10-091-2/+3
| |
* | added guard for torch.load to prevent loading pickles with unknown contentAUTOMATIC2022-10-091-0/+1
| |
* | change up #2056 to make it work how i want it to plus make xy plot write ↵AUTOMATIC2022-10-091-1/+1
| | | | | | | | correct values to images
* | Added extended model details to infotextWilliam Moorehouse2022-10-091-0/+1
| |
* | Fix typoNicolas Noullet2022-10-091-1/+1
| |
* | Fix VRAM Issue by only loading in hypernetwork when selected in settingsFampai2022-10-091-5/+2
| |
* | Merge pull request #1752 from Greendayle/dev/deepdanbooruAUTOMATIC11112022-10-091-0/+1
|\ \ | |/ |/| Added DeepDanbooru interrogator
| * Merge branch 'master' into dev/deepdanbooruGreendayle2022-10-081-0/+1
| |\
| * | made deepdanbooru optional, added to readme, automatic download of deepbooru ↵Greendayle2022-10-081-0/+1
| | | | | | | | | | | | model
* | | chore: Fix typosAidan Holland2022-10-081-3/+3
| | |
* | | Added ability to ignore last n layers in FrozenCLIPEmbedderFampai2022-10-081-0/+1
| |/ |/|
* | add --force-enable-xformers option and also add messages to console ↵AUTOMATIC2022-10-081-0/+1
|/ | | | regarding cross attention optimizations
* simplify xfrmers options: --xformers to enable and that's itAUTOMATIC2022-10-081-1/+1
|
* Merge pull request #1851 from C43H66N12O12S2/flashAUTOMATIC11112022-10-081-1/+2
|\ | | | | xformers attention
| * add xformers_available shared variableC43H66N12O12S22022-10-081-1/+1
| |
| * Update shared.pyC43H66N12O12S22022-10-071-0/+1
| |
* | do not let user choose his own prompt token count limitAUTOMATIC2022-10-081-3/+0
| |
* | check specifically for skippedTrung Ngo2022-10-081-1/+0
| |
* | Add button to skip the current iterationTrung Ngo2022-10-081-0/+5
| |
* | let user choose his own prompt token count limitAUTOMATIC2022-10-081-2/+3
| |
* | added support for hypernetworks (???)AUTOMATIC2022-10-071-1/+8
|/
* Removed duplicate defined models_pathMilly2022-10-061-10/+9
| | | | Use `modules.paths.models_path` instead `modules.shared.model_path`.
* Default window title progress updates onDepFA2022-10-061-1/+1
|
* Update shared.pyDepFA2022-10-061-0/+1
|
* integrate the new samplers PRAUTOMATIC2022-10-061-1/+0
|
* add variant settingC43H66N12O12S22022-10-061-0/+1
|
* option to let users select which samplers they want to hideAUTOMATIC2022-10-061-6/+9
|
* Set gradio-img2img-tool default to 'editor'DepFA2022-10-061-1/+1
|
* add editor to img2imgAUTOMATIC2022-10-041-0/+1
|
* option to not show images in web uiAUTOMATIC2022-10-041-0/+1
|
* Remove pycharm note, fix typoJustin Riddiough2022-10-041-2/+2
|
* Explain how to use second progress bar in pycharmJustin Riddiough2022-10-041-1/+1
|
* Modify --add-cpu descriptionbrkirch2022-10-041-1/+1
|
* Add BSRGAN to --add-cpubrkirch2022-10-041-3/+3
|
* Add --use-cpu command line optionbrkirch2022-10-041-2/+7
| | | | Remove MPS detection to use CPU for GFPGAN / CodeFormer and add a --use-cpu command line option.