aboutsummaryrefslogtreecommitdiffstats
path: root/modules
AgeCommit message (Collapse)AuthorLines
2022-10-16Added Refresh Button to embedding and hypernetwork names in Train TabJunpeng Qiu-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
2022-10-16Warn when user uses bad ui settingCookieHCl-1/+3
2022-10-16Use default value when dropdown ui setting is badCookieHCl-1/+1
Default value is the first value of selectables. Particually, None in styles.
2022-10-16Make style configurable in ui-config.jsonCookieHCl-0/+7
2022-10-16Allow specifying the region of ngrok.ddPn08-4/+7
2022-10-16honor --hide-ui-dir-config option for #2807AUTOMATIC-0/+2
2022-10-16added extras batch work from directorywinterspringsummer-5/+30
2022-10-16do not reload embeddings from disk when doing textual inversionAUTOMATIC-2/+4
2022-10-15Update sd_hijack.pyC43H66N12O12S2-1/+1
2022-10-15fix saving images compatibility with gradio updateAUTOMATIC-4/+1
2022-10-15Change vector size footer labelDepFA-1/+1
2022-10-15generalise to popular lossless formatsDepFA-6/+2
2022-10-15add webp for embed loadDepFA-0/+4
2022-10-15only save 1 image per embeddingDepFA-1/+4
2022-10-15add vector size to embed textDepFA-1/+7
2022-10-15check NaN for hypernetwork tuningAngelBottomless-4/+6
2022-10-15fix download section layoutruocaled-2/+2
2022-10-15typoNO_ob-1/+1
2022-10-15add First pass size always regardless of whether it was auto chosen or specifiedAUTOMATIC-1/+1
2022-10-15fix gadio issue with sending files between tabsAUTOMATIC-0/+8
2022-10-15change styling for top right corner UIAUTOMATIC-29/+28
made save style button not die when you cancel
2022-10-15bring back scale latent option in settingsAUTOMATIC-5/+6
2022-10-15fix new gradio failing to preserve image paramsAUTOMATIC-0/+18
2022-10-15re-apply height hacks to work with new gradioAUTOMATIC-2/+2
2022-10-15Merge branch 'master' into ckpt-cacheAUTOMATIC1111-137/+554
2022-10-15Disable compiling deepbooru modelCookieHCl-1/+1
This is only necessary when you have to train, and compiling model produces warning.
2022-10-15Merge branch 'master' into masterAUTOMATIC1111-122/+168
2022-10-15Set to -1 when seed input is nonegithublsx-1/+1
2022-10-15use "outdir_samples" if specifiedddPn08-1/+3
2022-10-15do not force relative paths in image historyddPn08-1/+1
2022-10-15Add hint for `ctrl/alt enter`aoirusann-2/+8
And duplicate implementations are removed
2022-10-15add option to use batch size for trainingAUTOMATIC-30/+54
2022-10-15bring history tab back, make it behave; it's still slow but won't fuck ↵AUTOMATIC-2/+2
anything up until you use it
2022-10-15reformat lines in images_history.pyAUTOMATIC-84/+98
2022-10-15rename firstpass w/h to discard old user settingsAUTOMATIC-2/+2
2022-10-14Raise an assertion error if no training images have been found.Melan-1/+2
2022-10-14set firstpass w/h to 0 by default and rever to old behavior when any are 0AUTOMATIC-21/+32
2022-10-14disabling history - i knew it was slow as fuck but i didn't realize it would ↵AUTOMATIC-2/+3
also show galleries on launch
2022-10-14add checkpoint cache option to UI for faster model switchingRae Fu-22/+33
switching time reduced from ~1500ms to ~280ms
2022-10-14remove duplicate code for log loss, add step, make it read from options ↵AUTOMATIC-32/+38
rather than gradio input
2022-10-14Merge remote-tracking branch 'Melanpan/master'AUTOMATIC-0/+34
2022-10-14change checkpoint merger to work in a more obvious wayAUTOMATIC-21/+7
remove sigmoid and inverse sigmoid because they just did the same thing as weighed sum only with changed multiplier
2022-10-14should fix the issue with missing layers in chechpoint mergerAUTOMATIC-1/+6
2022-10-14add option to read generation params for learning previews from txt2imgAUTOMATIC-15/+51
2022-10-14rework the code for lowram a bitAUTOMATIC-11/+4
2022-10-14load models to VRAM when using `--lowram` paramLjzd-PRO-2/+13
load models to VRM instead of RAM (for machines which have bigger VRM than RAM such as free Google Colab server)
2022-10-14add `--lowram` parameterLjzd-PRO-0/+1
load models to VRM instead of RAM (for machines which have bigger VRM than RAM such as free Google Colab server)
2022-10-14Add option to prevent empty spots in grid (2/2)Gugubo-1/+4
2022-10-14Add option to prevent empty spots in grid (1/2)Gugubo-0/+1
2022-10-14Change grid row count autodetect to prevent empty spotsGugubo-2/+3
Instead of just rounding (sometimes resulting in grids with "empty" spots), find a divisor. For example: 8 images will now result in a 4x2 grid instead of a 3x3 with one empty spot.