aboutsummaryrefslogtreecommitdiff
path: root/modules
AgeCommit message (Collapse)Author
2022-10-20updatediscus0434
2022-10-20default to ignore existing captionsDepFA
2022-10-20pass preprocess_txt_action paramDepFA
2022-10-20link existing txt optionDepFA
2022-10-20add existing caption file handlingDepFA
2022-10-20reorder create_hypernetwork paramsDepFA
2022-10-20pass overwrite old flagDepFA
2022-10-20split learn ratesDepFA
2022-10-20allow overwrite old embeddingDepFA
2022-10-20allow overwrite old hnDepFA
2022-10-20change html outputDepFA
2022-10-19Don't compute latent mask if were not using it. Also added support for fixed ↵random_thoughtss
highres_fix generation.
2022-10-19added support for ddim img2imgrandom_thoughtss
2022-10-19Fixed copying mistakerandom_thoughtss
2022-10-19Added support for RunwayML inpainting modelrandom_thoughtss
2022-10-19fix entropy point calculationcaptin411
2022-10-19update ui with extra training optionsDepFA
2022-10-19update training header textDepFA
2022-10-19generation_parameters_copypaste.py: fix indentMackerel
2022-10-19Send empty prompts as valid generation parameterVladimir Repin
2022-10-19Infotext saves more specific hypernet name.timntorres
2022-10-19Added a bit of padding to the leftAlexandre Simard
2022-10-19Update ui.pyAlexandre Simard
2022-10-19fix for #3086 failing to load any previous hypernetdiscus0434
2022-10-19fix for #3086 failing to load any previous hypernetAUTOMATIC
2022-10-19Update ui.pyDepFA
2022-10-20Merge branch 'AUTOMATIC1111:master' into masterdiscus0434
2022-10-19Merge pull request #3086 from discus0434/masterAUTOMATIC1111
Add settings for multi-layer structure hypernetworks
2022-10-19enable to write layer structure of hn himselfdiscus0434
2022-10-19layer options moves into create hnet uidiscus0434
2022-10-19UI changes for focal point image croppingcaptin411
2022-10-19Add auto focal point cropping to Preprocess imagescaptin411
This algorithm plots a bunch of points of interest on the source image and averages their locations to find a center. Most points come from OpenCV. One point comes from an entropy model. OpenCV points account for 50% of the weight and the entropy based point is the other 50%. The center of all weighted points is calculated and a bounding box is drawn as close to centered over that point as possible.
2022-10-19fix for broken checkpoint mergerAUTOMATIC
2022-10-19Fix typo in prompt_parser.pyIkko Ashimine
assoicated -> associated
2022-10-19Merge branch 'master' into test_resolve_conflictsMalumaDev
2022-10-19Merge branch 'master' into hot-reload-javascriptAUTOMATIC1111
2022-10-19Predictable long operation check for time estimationAnastasius
2022-10-19Estimated time displayed if jobs take more 60 secAnastasius
2022-10-19Added time left estimationAnastasius
2022-10-19Remove wrong self reference in CUDA support for invokeaiCheka
2022-10-19Merge branch 'master' into masterdiscus0434
2022-10-19Use training width/height when training hypernetworks.Silent
2022-10-19Merge branch 'master' into masterdiscus0434
2022-10-19Merge remote-tracking branch 'origin/api'AUTOMATIC
2022-10-19more careful loading of model weights (eliminates some issues with ↵AUTOMATIC
checkpoints that have weird cond_stage_model layer names)
2022-10-19call sampler by namearcticfaded
2022-10-19Image browser improvedyfszzx
2022-10-18provide sampler by namearcticfaded
2022-10-19updatediscus0434
2022-10-19updatediscus0434
generated by cgit v1.2.1 (git 2.18.0) at 2024-09-20 20:31:18 +0000