aboutsummaryrefslogtreecommitdiff
path: root/modules
AgeCommit message (Collapse)Author
2022-10-29Merge branch 'master' into modal-save-button-and-shortcutAUTOMATIC1111
2022-10-29Merge pull request #3691 from xmodar/arabicAUTOMATIC1111
Revamped Arabic localization
2022-10-29make existing image browser extension not breakAUTOMATIC
2022-10-29Merge branch 'Inspiron'AUTOMATIC
2022-10-29add needed imports fr new code in copypaste.pyAUTOMATIC
2022-10-29remove weird spaces added to ui.py over timeAUTOMATIC
2022-10-29fix open folder button not workingAUTOMATIC
2022-10-29skip filenames starting with . for img2img and extras batch modesAUTOMATIC
2022-10-29Merge pull request #3826 from ANTONIOPSD/patch-1AUTOMATIC1111
Natural sorting for dropdown checkpoint list
2022-10-29Merge pull request #3858 from R-N/log-csvAUTOMATIC1111
Fix log off by 1 #3847
2022-10-29Merge pull request #3803 from FlameLaw/masterAUTOMATIC1111
Fixed proper dataset shuffling
2022-10-29Merge pull request #3669 from random-thoughtss/masterAUTOMATIC1111
Added option to use unmasked conditioning image for inpainting model.
2022-10-29Merge pull request #3874 from cobryan05/extra_tweakAUTOMATIC1111
Extras Tab - Option to upscale before face fix, caching improvements
2022-10-29change default hypernet activation function to linearAUTOMATIC
2022-10-29Merge pull request #3877 from Yaiol/masterAUTOMATIC1111
Filename tags are wrongly referencing to process size instead of image size
2022-10-29Merge pull request #3717 from benkyoujouzu/masterAUTOMATIC1111
Add missing support for linear activation in hypernetwork
2022-10-29Merge pull request #3771 from aria1th/patch-12AUTOMATIC1111
Disable unavailable or duplicate options for Activation functions
2022-10-28Merge branch 'AUTOMATIC1111:master' into masterBruno Seoane
2022-10-29Re enable linearAngelBottomless
2022-10-29Update images.pyYaiol
Filename tags [height] and [width] are wrongly referencing to process size instead of resulting image size. Making all upscale files named wrongly.
2022-10-28extras: upscaler blending should not be considered in cache keyChris OBryan
2022-10-28extras-tweaks: autoformat changed linesChris OBryan
2022-10-28extras: Make image cache LRUChris OBryan
This changes the extras image cache into a Least-Recently-Used cache. This allows more experimentation with different upscalers without missing the cache. Max cache size is increased to 5 and is cleared on source image update.
2022-10-28extras: Rework image cacheChris OBryan
Bit of a refactor to the image cache to make it easier to extend. Also takes into account the entire image instead of just a cropped portion.
2022-10-28extras: Add option to run upscaling before face fixingChris OBryan
Face restoration can look much better if ran after upscaling, as it allows the restoration to fix upscaling artifacts. This patch adds an option to choose which order to run upscaling/face fixing in.
2022-10-28Fix log off by 1Muhammad Rizqi Nur
2022-10-28Always ignore "None.pt" in the hypernet directory.timntorres
2022-10-27Explicitly state when Hypernet is none.timntorres
2022-10-27Read hypernet strength from PNG info.timntorres
2022-10-27Add strength to textinfo.timntorres
2022-10-28Add missing support for linear activation in hypernetworkbenkyoujouzu
2022-10-28Natural sorting for dropdown checkpoint listAntonio
Example: Before After 11.ckpt 11.ckpt ab.ckpt ab.ckpt ade_pablo_step_1000.ckpt ade_pablo_step_500.ckpt ade_pablo_step_500.ckpt ade_pablo_step_1000.ckpt ade_step_1000.ckpt ade_step_500.ckpt ade_step_1500.ckpt ade_step_1000.ckpt ade_step_2000.ckpt ade_step_1500.ckpt ade_step_2500.ckpt ade_step_2000.ckpt ade_step_3000.ckpt ade_step_2500.ckpt ade_step_500.ckpt ade_step_3000.ckpt atp_step_5500.ckpt atp_step_5500.ckpt model1.ckpt model1.ckpt model10.ckpt model10.ckpt model1000.ckpt model33.ckpt model33.ckpt model50.ckpt model400.ckpt model400.ckpt model50.ckpt model1000.ckpt moo44.ckpt moo44.ckpt v1-4-pruned-emaonly.ckpt v1-4-pruned-emaonly.ckpt v1-5-pruned-emaonly.ckpt v1-5-pruned-emaonly.ckpt v1-5-pruned.ckpt v1-5-pruned.ckpt v1-5-vae.ckpt v1-5-vae.ckpt
2022-10-27Reduce peak memory usage when changing modelsJosh Watzman
A few tweaks to reduce peak memory usage, the biggest being that if we aren't using the checkpoint cache, we shouldn't duplicate the model state dict just to immediately throw it away. On my machine with 16GB of RAM, this change means I can typically change models, whereas before it would typically OOM.
2022-10-27Add a barebones interrogate APIRoy Shilkrot
2022-10-27Updated name and hover text.random_thoughtss
2022-10-27Moved mask weight config to SD sectionrandom_thoughtss
2022-10-27Highres fix works with unmasked latent.random_thoughtss
Also refactor the mask creation to make it more accesible.
2022-10-27Merge branch 'AUTOMATIC1111:master' into masterrandom-thoughtss
2022-10-28Fix random dataset shuffle on TIFlameLaw
2022-10-27fixed indentationFlorian Horn
2022-10-27added save button and shortcut (s) to Modal ViewFlorian Horn
2022-10-27create send to buttons by extensionsyfszzx
2022-10-27Disable unavailable or duplicate optionsAngelBottomless
2022-10-27Revert unresolved changes in Bias initializationAngelBottomless
it should be zeros_ or parameterized in future properly.
2022-10-27Fix dropout logicguaneec
2022-10-27Squashed commit of fixing dropout silentlyAngelBottomless
fix dropouts for future hypernetworks add kwargs for Hypernetwork class hypernet UI for gradio input add recommended options remove as options revert adding options in ui
2022-10-27create send to buttons in one moduleyfszzx
2022-10-26Add id access to scripts list in the cssxmodar
2022-10-26fix: Correct before image saved callbackMMaker
2022-10-26prototype progress apievshiron
generated by cgit v1.2.1 (git 2.18.0) at 2025-05-28 17:29:15 +0000