aboutsummaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
...
| * | | Fix XY-plot steps if highres fix is enabledspace-nuko2022-10-141-1/+4
| | | |
* | | | Merge pull request #2661 from Melanpan/masterAUTOMATIC11112022-10-151-0/+1
|\ \ \ \ | | | | | | | | | | Raise an assertion error if no training images have been found.
| * \ \ \ Merge branch 'master' into masterAUTOMATIC11112022-10-1511-139/+219
| |\ \ \ \ | |/ / / / |/| | | |
* | | | | Set to -1 when seed input is nonegithublsx2022-10-151-1/+1
| | | | |
* | | | | Move index_url args into run_pip.Cassy-Lee2022-10-151-8/+8
| | | | |
* | | | | Update launch.pyCassy-Lee2022-10-151-6/+7
| | | | | | | | | | | | | | | Allow change set --index-url for pip.
* | | | | 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`aoirusann2022-10-153-14/+10
| | | | | | | | | | | | | | | | | | | | And duplicate implementations are removed
* | | | | remove extra 100ms timeoutruocaled2022-10-151-3/+1
| | | | |
* | | | | re-attach full screen zoom listenersruocaled2022-10-151-0/+3
| | | | |
* | | | | allow re-open for multiple images galleryruocaled2022-10-151-3/+4
| | | | |
* | | | | fix observer disconnect logicruocaled2022-10-151-5/+7
| | | | |
* | | | | remove console.logruocaled2022-10-151-1/+0
| | | | |
* | | | | auto re-open selected image after re-generation ruocaled2022-10-151-0/+32
| | | | | | | | | | | | | | | | | | | | | | | | | attach an observer of gallery when generation in progress, if there was a image selected in gallery and gallery has only 1 image, auto re-select/open that image. This matches behavior of prior to Gradio 3.4.1 version bump, is a quality of life feature many people enjoyed.
* | | | | 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 ↵AUTOMATIC2022-10-142-6/+14
| | | | | | | | | | | | | | | | | | | | 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
| | | |
* | | | remove the other DenoisingAUTOMATIC2022-10-141-1/+0
| | | |
* | | | [xy_grid.py] add option denoising_strengthNaeaeaeaeae2022-10-141-0/+1
| | | |
* | | | change checkpoint merger to work in a more obvious wayAUTOMATIC2022-10-143-23/+9
| | | | | | | | | | | | | | | | remove sigmoid and inverse sigmoid because they just did the same thing as weighed sum only with changed multiplier
* | | | regression in xy_grid Var. seed fixingRnDMonkey2022-10-141-1/+1
| | | |
* | | | fix typoChucklesTheBeard2022-10-141-1/+1
| | | |
* | | | should fix the issue with missing layers in chechpoint mergerAUTOMATIC2022-10-141-1/+6
| | | |
* | | | restore borders for promptsAUTOMATIC2022-10-141-8/+0
| | | |
* | | | 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
| | | |
* | | | load models to VRAM when using `--lowram` paramLjzd-PRO2022-10-141-2/+13
| | | | | | | | | | | | load models to VRM instead of RAM (for machines which have bigger VRM than RAM such as free Google Colab server)
* | | | add `--lowram` parameterLjzd-PRO2022-10-141-0/+1
| | | | | | | | | | | | load models to VRM instead of RAM (for machines which have bigger VRM than RAM such as free Google Colab server)
* | | | Add option to prevent empty spots in grid (2/2)Gugubo2022-10-141-1/+4
| | | |
* | | | Add option to prevent empty spots in grid (1/2)Gugubo2022-10-141-0/+1
| | | |
* | | | Change grid row count autodetect to prevent empty spotsGugubo2022-10-141-2/+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.
* | | | remove user's liners from .gitigbore - those go into .git/info/excludeAUTOMATIC2022-10-141-2/+0
| | | |
* | | | Merge pull request #2396 from yfszzx/masterAUTOMATIC11112022-10-144-0/+375
|\ \ \ \ | | | | | | | | | | Add a "History" tab
| * \ \ \ Merge branch 'AUTOMATIC1111:master' into master不会画画的中医不是好程序员2022-10-143-14/+33
| |\ \ \ \
| * \ \ \ \ Merge branch 'master' of https://github.com/yfszzx/stable-diffusion-webui-plusyfszzx2022-10-1417-60/+210
| |\ \ \ \ \
| | * \ \ \ \ Merge branch 'AUTOMATIC1111:master' into master不会画画的中医不是好程序员2022-10-1317-60/+210
| | |\ \ \ \ \
| * | | | | | | fix deep nesting directories problemyfszzx2022-10-141-34/+42
| |/ / / / / /
| * | | | | | images history fix all known bugyfszzx2022-10-135-41/+40
| | | | | | |
| * | | | | | Merge branch 'AUTOMATIC1111:master' into master不会画画的中医不是好程序员2022-10-139-133/+200
| |\ \ \ \ \ \ | | | |_|/ / / | | |/| | | |
| * | | | | | images history delete a number of images consecutively nextyfszzx2022-10-132-29/+39
| | | | | | |
| * | | | | | Merge branch 'master' of https://github.com/yfszzx/stable-diffusion-webui-plusyfszzx2022-10-124-2/+265
| |\ \ \ \ \ \