aboutsummaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Merge remote-tracking branch 'origin/steve3d'AUTOMATIC2022-10-121-1/+1
|\
| * Update shared.pysupersteve3d2022-10-121-1/+1
| | | | | | Correct typo to "Unload VAE and CLIP from VRAM when training" in settings tab.
* | Merge pull request #2143 from JC-Array/deepdanbooru_pre_processAUTOMATIC11112022-10-124-27/+114
|\ \ | | | | | | deepbooru tags for textual inversion preproccessing
| * | resolved conflicts, moved settings under interrogate section, settings only ↵JC_Array2022-10-114-13/+12
| | | | | | | | | | | | show if deepbooru flag is enabled
| * | Merge branch 'AUTOMATIC1111:master' into deepdanbooru_pre_processJC-Array2022-10-1130-239/+881
| |\|
| * | removed unneeded printJC_Array2022-10-111-1/+0
| | |
| * | added alpha sort and threshold variables to create process method in ↵JC_Array2022-10-101-1/+1
| | | | | | | | | | | | preprocessing
| * | Merge pull request #2 from JC-Array/masterJC-Array2022-10-1023-68/+1233
| |\ \ | | | | | | | | resolve merge conflicts
| | * \ Merge branch 'deepdanbooru_pre_process' into masterJC-Array2022-10-104-22/+111
| | |\ \ | | |/ / | |/| |
| * | | added deepbooru settings (threshold and sort by alpha or likelyhood)JC_Array2022-10-102-11/+31
| | | |
| * | | corrected tag return in get_deepbooru_tagsJC_Array2022-10-101-1/+0
| | | |
| * | | import time missing, added to deepbooru fixxing error on get_deepbooru_tagsJC_Array2022-10-101-0/+1
| | | |
| * | | removed change in last commit, simplified to adding the visible argument to ↵JC_Array2022-10-101-12/+10
| | | | | | | | | | | | | | | | process_caption_deepbooru and it set to False if deepdanbooru argument is not set
| * | | removed duplicate run_preprocess.click by creating run_preprocess_inputs ↵JC_Array2022-10-101-32/+17
| | | | | | | | | | | | | | | | list and appending deepbooru variable to input list if in scope
| * | | refactored the deepbooru module to improve speed on running multiple ↵JC_Array2022-10-103-36/+122
| | | | | | | | | | | | | | | | interogations in a row. Added the option to generate deepbooru tags for textual inversion preproccessing.
| | * | Merge pull request #1 from AUTOMATIC1111/masterJC-Array2022-10-1023-68/+1233
| |/| | | | | | | | | | updating files to resolve merge conflicts
* | | | Truncate error text to fix service lockup / stallGreg Fuller2022-10-121-1/+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
* | | | create dir for hypernetworksAUTOMATIC2022-10-121-0/+1
| |_|/ |/| |
* | | reports that training with medvram is possible.AUTOMATIC2022-10-112-2/+2
| | |
* | | Merge remote-tracking branch 'origin/master'AUTOMATIC2022-10-111-0/+3
|\ \ \
| * | | triggers 'input' event when using arrow keys to edit attentionnai-degen2022-10-111-0/+3
| | | |
* | | | apply lr schedule to hypernetsAUTOMATIC2022-10-114-45/+54
| | | |
* | | | Merge pull request #1795 from MarkovInequality/learnscheduleAUTOMATIC11112022-10-112-5/+51
|\ \ \ \ | |/ / / |/| | | Added learning_rate scheduling for TI
| * | | Merge branch 'learning_rate-scheduling' into learnscheduleAUTOMATIC11112022-10-1133-272/+1956
| |\ \ \ | |/ / / |/| | |
* | | | bump gradio to 3.4.1AUTOMATIC2022-10-113-2/+13
| | | |
* | | | prevent extra modules from being saved/loaded with hypernetAUTOMATIC2022-10-111-1/+1
| | | |
* | | | add an option to unload models during hypernetwork training to save VRAMAUTOMATIC2022-10-115-18/+46
| | | |
* | | | produce error when training with medvram/lowvram enabledAUTOMATIC2022-10-112-0/+5
| | | |
* | | | add option to select hypernetwork modules when creatingAUTOMATIC2022-10-113-4/+6
| | | |
* | | | change default for XY plot's Y to Nothing.AUTOMATIC2022-10-111-1/+1
| | | |
* | | | Merge pull request #2201 from alg-wiki/textual__inversionAUTOMATIC11112022-10-113-10/+11
|\ \ \ \ | | | | | | | | | | Textual Inversion: Preprocess and Training will only pick-up image files instead
| * | | | Removed my local edits to checkpoint image generationalg-wiki2022-10-111-5/+2
| | | | |
| * | | | Switched to exception handlingalg-wiki2022-10-113-18/+18
| | | | |
| * | | | Added .webp .bmpalg-wiki2022-10-103-3/+3
| | | | |
| * | | | Merge branch 'master' into textual__inversionalg-wiki2022-10-1019-48/+1194
| |\ \ \ \
| * | | | | Textual Inversion: Preprocess and Training will only pick-up image filesalg-wiki2022-10-103-3/+6
| | | | | |
| * | | | | Custom Width and Heightalg-wiki2022-10-104-23/+26
| | | | | |
| * | | | | Fixed progress bar output for epochalg-wiki2022-10-101-1/+1
| | | | | |
| * | | | | Textual Inversion: Added custom training image size and number of repeats ↵alg-wiki2022-10-104-9/+24
| | | | | | | | | | | | | | | | | | | | | | | | per input image in a single epoch
* | | | | | Use apply_hypernetwork functionbrkirch2022-10-111-10/+4
| | | | | |
* | | | | | Add InvokeAI and lstein to credits, add back CUDA supportbrkirch2022-10-112-0/+14
| | | | | |
* | | | | | Add check for psutilbrkirch2022-10-112-6/+23
| | | | | |
* | | | | | Add cross-attention optimization from InvokeAIbrkirch2022-10-113-3/+86
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * Add cross-attention optimization from InvokeAI (~30% speed improvement on MPS) * Add command line option for it * Make it default when CUDA is unavailable
* | | | | | Merge pull request #2227 from papuSpartan/masterAUTOMATIC11112022-10-112-0/+3
|\ \ \ \ \ \ | | | | | | | | | | | | | | Refresh list of models/ckpts upon hitting restart gradio in the setti…
| * | | | | | move list refresh to webui.py and add stdout indicating it's doing sopapuSpartan2022-10-112-3/+2
| | | | | | |
| * | | | | | Refresh list of models/ckpts upon hitting restart gradio in the settings panepapuSpartan2022-10-111-0/+4
| | |_|_|_|/ | |/| | | |
* | | | | | add codeowners file so stop the great guys who are collaborating on the ↵AUTOMATIC2022-10-111-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | project from merging in PRs.
* | | | | | become even stricter with picklesAUTOMATIC2022-10-111-0/+17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | no pickle shall pass thank you again, RyotaK
* | | | | | Merge pull request #2218 from AUTOMATIC1111/update-readmeC43H66N12O12S22022-10-111-2/+8
|\ \ \ \ \ \ | | | | | | | | | | | | | | add features, credit for composable diffusion
| * | | | | | Update README.mdClashSAN2022-10-111-1/+1
| | | | | | |
generated by cgit v1.2.3 (git 2.25.1) at 2025-05-05 22:06:52 +0000