aboutsummaryrefslogtreecommitdiffstats
AgeCommit message (Collapse)AuthorLines
2022-10-13Restore last generation paramsTrung Ngo-1/+14
2022-10-13Merge branch 'master' of https://github.com/HunterVacui/stable-diffusion-webuiGreg Fuller-1/+1
2022-10-13Merge pull request #2324 from HunterVacui/interrogate_include_ranks_in_outputAUTOMATIC1111-14/+24
Interrogate: add option to include ranks in output
2022-10-13add missing id propertyDepFA-1/+1
2022-10-13remove interrogate option I accidentally deletedAUTOMATIC-0/+1
2022-10-13Merge branch 'AUTOMATIC1111:master' into master不会画画的中医不是好程序员-133/+200
2022-10-13images history delete a number of images consecutively nextyfszzx-29/+39
2022-10-12Add drag/drop param loading.d8ahazard-1/+74
Drop an image or generational text onto the prompt bar, it loads the info for parsing.
2022-10-12Save a csv containing the loss while trainingMelan-2/+35
2022-10-12[3/?] [wip] fix incorrect variable referenceGreg Fuller-1/+1
still needs testing
2022-10-12[2/?] [wip] ignore OPT_INCLUDE_RANKS for training filenamesGreg Fuller-2/+5
2022-10-12[1/?] [wip] Reintroduce opts.interrogate_return_ranksGreg Fuller-11/+14
looks functionally correct, needs testing Needs particular testing care around whether the colon usage (:) will break anything in whatever new use cases were introduced by https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/2143
2022-10-12Merge remote-tracking branch 'upstream/master' into ↵Greg Fuller-224/+705
interrogate_include_ranks_in_output
2022-10-12deepbooru: added option to use spaces or underscoresAUTOMATIC-71/+95
deepbooru: added option to quote (\) in tags deepbooru/BLIP: write caption to file instead of image filename deepbooru/BLIP: now possible to use both for captions deepbooru: process is stopped even if an exception occurs
2022-10-12train: change filename processing to be more simple and configurableAUTOMATIC-62/+105
train: make it possible to make text files with prompts train: rework scheduler so that there's less repeating code in textual inversion and hypernets train: move epochs setting to options
2022-10-13Merge branch 'master' of https://github.com/yfszzx/stable-diffusion-webui-plusyfszzx-2/+265
2022-10-13images history improvementyfszzx-3/+3
2022-10-13Merge branch 'AUTOMATIC1111:master' into master不会画画的中医不是好程序员-2/+265
2022-10-13images history improvementyfszzx-2/+2
2022-10-13images history improvementyfszzx-84/+88
2022-10-12testyfszzx-171/+565
2022-10-12Merge pull request #2037 from AUTOMATIC1111/embed-embeddings-in-imagesAUTOMATIC1111-2/+265
Add option to store TI embeddings in png chunks, and load from same.
2022-10-12Merge branch 'master' of https://github.com/yfszzx/stable-diffusion-webui-plusyfszzx-62/+128
2022-10-12images history improvementyfszzx-100/+190
2022-10-12formattingDepFA-11/+11
2022-10-12formattingDepFA-79/+91
2022-10-12fix iterator bug for #2295AUTOMATIC-4/+4
2022-10-12Remove duplicate artist from fileKalle-1/+0
2022-10-12Account when lines are mismatchedhentailord85ez-1/+11
2022-10-12change textual inversion tab to trainAUTOMATIC-14/+10
remake train interface to use tabs
2022-10-12xy_grid: Refactor confirm functionsMilly-34/+39
2022-10-12xy_grid: Confirm that hypernetwork options are valid before startingMilly-0/+12
2022-10-12xy_grid: Find hypernetwork by closest nameMilly-1/+16
2022-10-12Merge pull request #2110 from JustMaier/feature/scale_toAUTOMATIC1111-27/+50
Add "Scale to" option to Extras
2022-10-12Merge branch 'master' into feature/scale_toAUTOMATIC1111-327/+2228
2022-10-12Typo fix in watermark hint.LunixWasTaken-1/+1
2022-10-12[img2imgalt] Fix seed & Allow batch.aoirusann-3/+1
2022-10-12Ensure the directory exists before saving to itbrkirch-0/+2
The directory for the images saved with the Save button may still not exist, so it needs to be created prior to opening the log.csv file.
2022-10-12emergency fixAUTOMATIC-1/+2
2022-10-12update environment-wsl2.yamlJames Noeckel-5/+5
2022-10-12Merge pull request #2312 from AUTOMATIC1111/edit-attention-nan-fixAUTOMATIC1111-0/+1
edit attention key handler: return early when weight parse returns NaN
2022-10-12prevent SD model from loading when running in deepdanbooru processAUTOMATIC-12/+14
2022-10-12just add the deepdanbooru settings unconditionallyAUTOMATIC-9/+4
2022-10-12Merge remote-tracking branch 'origin/steve3d'AUTOMATIC-1/+1
2022-10-12Merge pull request #2143 from JC-Array/deepdanbooru_pre_processAUTOMATIC1111-27/+114
deepbooru tags for textual inversion preproccessing
2022-10-12Truncate error text to fix service lockup / stallGreg Fuller-1/+8
What: * Update wrap_gradio_call to add a limit to the maximum amount of text output Why: * wrap_gradio_call currently prints out a list of the arguments provided to the failing function. * if that function is save_image, this causes the entire image to be printed to stderr * If the image is large, this can cause the service to lock up while attempting to print all the text * It is easy to generate large images using the x/y plot script * it is easy to encounter image save exceptions, including if the output directory does not exist / cannot be written to, or if the file is too big * The huge amount of log spam is confusing and not particularly helpful
2022-10-12create dir for hypernetworksAUTOMATIC-0/+1
2022-10-11Interrogate: add option to include ranks in outputGreg Fuller-10/+17
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)
2022-10-12Update shared.pysupersteve3d-1/+1
Correct typo to "Unload VAE and CLIP from VRAM when training" in settings tab.
2022-10-12Prevent nans from failed float parsing from overwriting weightsDepFA-0/+1