aboutsummaryrefslogtreecommitdiffstats
path: root/modules
Commit message (Collapse)AuthorAgeFilesLines
* fix dir_path in some path like `D:/Pic/outputs`DancingSnow2022-10-161-4/+2
|
* Better readablity of logsCookieHCl2022-10-162-2/+2
|
* Only make output dir when creating outputCookieHCl2022-10-162-7/+4
|
* Fix FileNotFoundError in history tabCookieHCl2022-10-161-4/+8
| | | | Now only traverse images when directory exists
* Added Refresh Button to embedding and hypernetwork names in Train TabJunpeng Qiu2022-10-161-19/+26
| | | | | | | | | | | | | | | Problem everytime I modified pt files in embedding_dir or hypernetwork_dir, I need to restart webui to have the new files shown in the dropdown of Train Tab Solution refactored create_refresh_button out of create_setting_component so we can use this method to create button next to gr.Dropdowns of embedding name and hypernetworks Extra Modification hypernetwork pt are now sorted in alphabetic order
* Warn when user uses bad ui settingCookieHCl2022-10-161-1/+3
|
* Use default value when dropdown ui setting is badCookieHCl2022-10-161-1/+1
| | | | | Default value is the first value of selectables. Particually, None in styles.
* Make style configurable in ui-config.jsonCookieHCl2022-10-161-0/+7
|
* Allow specifying the region of ngrok.ddPn082022-10-163-4/+7
|
* honor --hide-ui-dir-config option for #2807AUTOMATIC2022-10-161-0/+2
|
* added extras batch work from directorywinterspringsummer2022-10-162-5/+30
|
* do not reload embeddings from disk when doing textual inversionAUTOMATIC2022-10-162-2/+4
|
* Update sd_hijack.pyC43H66N12O12S22022-10-151-1/+1
|
* fix saving images compatibility with gradio updateAUTOMATIC2022-10-151-4/+1
|
* Change vector size footer labelDepFA2022-10-151-1/+1
|
* generalise to popular lossless formatsDepFA2022-10-151-6/+2
|
* add webp for embed loadDepFA2022-10-151-0/+4
|
* only save 1 image per embeddingDepFA2022-10-151-1/+4
|
* add vector size to embed textDepFA2022-10-151-1/+7
|
* check NaN for hypernetwork tuningAngelBottomless2022-10-151-4/+6
|
* fix download section layoutruocaled2022-10-151-2/+2
|
* typoNO_ob2022-10-151-1/+1
|
* add First pass size always regardless of whether it was auto chosen or specifiedAUTOMATIC2022-10-151-1/+1
|
* fix gadio issue with sending files between tabsAUTOMATIC2022-10-151-0/+8
|
* change styling for top right corner UIAUTOMATIC2022-10-151-29/+28
| | | | made save style button not die when you cancel
* bring back scale latent option in settingsAUTOMATIC2022-10-152-5/+6
|
* fix new gradio failing to preserve image paramsAUTOMATIC2022-10-151-0/+18
|
* re-apply height hacks to work with new gradioAUTOMATIC2022-10-151-2/+2
|
* Merge branch 'master' into ckpt-cacheAUTOMATIC11112022-10-1515-137/+554
|\
| * Disable compiling deepbooru modelCookieHCl2022-10-151-1/+1
| | | | | | | | | | This is only necessary when you have to train, and compiling model produces warning.
| * Merge branch 'master' into masterAUTOMATIC11112022-10-156-122/+168
| |\
| | * Set to -1 when seed input is nonegithublsx2022-10-151-1/+1
| | |
| | * use "outdir_samples" if specifiedddPn082022-10-151-1/+3
| | |
| | * do not force relative paths in image historyddPn082022-10-151-1/+1
| | |
| | * Add hint for `ctrl/alt enter`aoirusann2022-10-151-2/+8
| | | | | | | | | | | | And duplicate implementations are removed
| | * add option to use batch size for trainingAUTOMATIC2022-10-154-30/+54
| | |
| | * bring history tab back, make it behave; it's still slow but won't fuck ↵AUTOMATIC2022-10-141-2/+2
| | | | | | | | | | | | anything up until you use it
| | * reformat lines in images_history.pyAUTOMATIC2022-10-141-84/+98
| | |
| | * rename firstpass w/h to discard old user settingsAUTOMATIC2022-10-141-2/+2
| | |
| * | Raise an assertion error if no training images have been found.Melan2022-10-141-1/+2
| |/
| * set firstpass w/h to 0 by default and rever to old behavior when any are 0AUTOMATIC2022-10-142-21/+32
| |
| * disabling history - i knew it was slow as fuck but i didn't realize it would ↵AUTOMATIC2022-10-141-2/+3
| | | | | | | | also show galleries on launch
| * remove duplicate code for log loss, add step, make it read from options ↵AUTOMATIC2022-10-144-32/+38
| | | | | | | | rather than gradio input
| * Merge remote-tracking branch 'Melanpan/master'AUTOMATIC2022-10-143-0/+34
| |\
| | * Add learn_rate to csv and removed a left-over debug statementMelan2022-10-132-5/+6
| | |
| | * Save a csv containing the loss while trainingMelan2022-10-123-2/+35
| | |
| * | change checkpoint merger to work in a more obvious wayAUTOMATIC2022-10-142-21/+7
| | | | | | | | | | | | remove sigmoid and inverse sigmoid because they just did the same thing as weighed sum only with changed multiplier
| * | should fix the issue with missing layers in chechpoint mergerAUTOMATIC2022-10-141-1/+6
| | |
| * | add option to read generation params for learning previews from txt2imgAUTOMATIC2022-10-143-15/+51
| | |
| * | rework the code for lowram a bitAUTOMATIC2022-10-142-11/+4
| | |
generated by cgit v1.2.3 (git 2.25.1) at 2025-05-07 11:52:07 +0000