aboutsummaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Merge branch 'master' of https://github.com/bamarillo/stable-diffusion-webuiBruno Seoane2022-10-2310-304/+1119
|\
| * Merge pull request #2067 from victorca25/esrgan_modAUTOMATIC11112022-10-234-292/+563
| |\ | | | | | | update ESRGAN architecture and model to support all ESRGAN models
| | * Merge branch 'master' into esrgan_modvictorca252022-10-096-10/+13
| | |\
| | * | update ESRGAN architecture and model to support all ESRGAN models in the DB, ↵victorca252022-10-095-320/+591
| | | | | | | | | | | | | | | | BSRGAN and real-ESRGAN models
| * | | after initial launch, disable --autolaunch for subsequent restartsw-e-w2022-10-231-0/+2
| | | |
| * | | Add ru_RU localizationkabachuha2022-10-231-0/+475
| | | |
| * | | working maskStephen2022-10-231-8/+12
| | | |
| * | | non-implemented mask with any typeStephen2022-10-233-2/+6
| | | |
| * | | [API][Feature] - Add img2img API endpointStephen2022-10-233-8/+63
| | | |
| * | | Update hypernetwork.pyDepFA2022-10-231-4/+7
| | | |
* | | | Add batch processing "extras" endpointBruno Seoane2022-10-232-3/+37
| | | |
* | | | Update run_extras to use the temp filenameBruno Seoane2022-10-231-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In batch mode run_extras tries to preserve the original file name of the images. The problem is that this makes no sense since the user only gets a list of images in the UI, trying to manually save them shows that this images have random temp names. Also, trying to keep "orig_name" in the API is a hassle that adds complexity to the consuming UI since the client has to use (or emulate) an input (type=file) element in a form. Using the normal file name not only doesn't change the output and functionality in the original UI but also helps keep the API simple.
* | | | Add "extra" single image operationBruno Seoane2022-10-232-6/+63
| | | | | | | | | | | | | | | | | | | | | | | | - Separate extra modes into 3 endpoints so the user ddoesn't ahve to handle so many unused parameters. - Add response model for codumentation
* | | | Moved moodels to their own file and extracted base64 conversion to its own ↵Bruno Seoane2022-10-222-11/+14
| | | | | | | | | | | | | | | | function
* | | | Remove unused importsBruno Seoane2022-10-221-4/+1
|/ / /
* | | Allow tracking real-time lossAngelBottomless2022-10-221-1/+1
| | | | | | | | | | | | Someone had 6000 images in their dataset, and it was shown as 0, which was confusing. This will allow tracking real time dataset-average loss for registered objects.
* | | fix for img2img color correction in a batch #3218AUTOMATIC2022-10-221-2/+4
| | |
* | | add --freeze-settings commandline argument to disable changing settingsAUTOMATIC2022-10-222-2/+10
| | |
* | | removed the option to use 2x more memory when generating previewsAUTOMATIC2022-10-223-29/+14
| | | | | | | | | | | | | | | added an option to always only show one image in previews removed duplicate code
* | | Generate grid preview for progress imageUnnoen2022-10-223-2/+30
| | |
* | | Update hypernetwork.pyAngelBottomless2022-10-221-11/+44
| | |
* | | call model_loaded_callback after setting shared.sd_model in case scripts ↵AUTOMATIC2022-10-221-1/+2
| | | | | | | | | | | | refer to it using that
* | | fix aesthetic gradients doing nothing after loading a different modelMrCheeze2022-10-221-2/+2
| | |
* | | record First pass size as 0x0 for #3328AUTOMATIC2022-10-221-1/+2
| | |
* | | improve ja translationKris572022-10-221-14/+14
| | |
* | | improve ja translationKris572022-10-221-33/+33
| | |
* | | improve ja translationKris572022-10-221-24/+24
| | |
* | | improve ja translationKris572022-10-221-46/+46
| | |
* | | add ja translationKris572022-10-221-64/+64
| | |
* | | add ja translationKris572022-10-221-24/+24
| | |
* | | add ja localizationKris572022-10-221-0/+413
| | |
* | | Fixed img2imgalt after inpainting updaterandom_thoughtss2022-10-221-1/+7
| | |
* | | Merge pull request #3414 from discus0434/masterAUTOMATIC11112022-10-223-40/+63
|\ \ \ | | | | | | | | [Hypernetworks] Add a feature to use dropout / more activation functions
| * | | small fixdiscus04342022-10-221-4/+3
| | | |
| * | | Merge branch 'AUTOMATIC1111:master' into masterdiscus04342022-10-222-0/+14
| |\ \ \
| * | | | small fixdiscus04342022-10-222-8/+5
| | | | |
| * | | | add an option to avoid dying reludiscus04342022-10-221-6/+6
| | | | |
| * | | | Merge branch 'master' of upstreamdiscus04342022-10-2235-524/+1568
| |\ \ \ \
| * | | | | add dropoutdiscus04342022-10-223-51/+70
| | | | | |
| * | | | | Merge pull request #2 from aria1th/patch-6discus04342022-10-221-8/+15
| |\ \ \ \ \ | | | | | | | | | | | | | | generalized some functions and option for ignoring first layer
| | * | | | | Revert "fix bugs and optimizations"aria1th2022-10-201-59/+46
| | | | | | | | | | | | | | | | | | | | | | | | | | | | This reverts commit 108be15500aac590b4e00420635d7b61fccfa530.
| | * | | | | fix bugs and optimizationsAngelBottomless2022-10-201-46/+59
| | | | | | |
| | * | | | | only linearAngelBottomless2022-10-201-5/+5
| | | | | | |
| | * | | | | generalized some functions and option for ignoring first layerAngelBottomless2022-10-201-8/+15
| |/ / / / /
* | | | | | fix part2Greendayle2022-10-221-1/+1
| | | | | |
* | | | | | Deepdanbooru linux fixGreendayle2022-10-221-1/+2
| | | | | |
* | | | | | typoAUTOMATIC2022-10-221-1/+1
| | | | | |
* | | | | | added callback for creating new settings in extensionsAUTOMATIC2022-10-223-3/+33
| |_|/ / / |/| | | |
* | | | | added a guard for hypernet training that will stop early if weights are ↵AUTOMATIC2022-10-221-0/+11
| | | | | | | | | | | | | | | | | | | | getting no gradients
* | | | | fix for extensions without style.cssAUTOMATIC2022-10-221-0/+3
| |/ / / |/| | |