Age | Commit message (Collapse) | Author | Lines | |
---|---|---|---|---|
2022-10-23 | Add folder processing endpoint | Bruno Seoane | -27/+35 | |
Also minor refactor | ||||
2022-10-23 | Move processing's models into models.py | Bruno Seoane | -156/+119 | |
It didn't make sense to have two differente files for the same and "models" is a more descriptive name. | ||||
2022-10-23 | Update endpoints to use gradio's own utils functions | Bruno Seoane | -41/+38 | |
2022-10-23 | Merge branch 'master' of https://github.com/bamarillo/stable-diffusion-webui | Bruno Seoane | -304/+642 | |
2022-10-23 | Add batch processing "extras" endpoint | Bruno Seoane | -3/+37 | |
2022-10-23 | Update run_extras to use the temp filename | Bruno Seoane | -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. | ||||
2022-10-23 | Merge pull request #2067 from victorca25/esrgan_mod | AUTOMATIC1111 | -292/+563 | |
update ESRGAN architecture and model to support all ESRGAN models | ||||
2022-10-23 | working mask | Stephen | -8/+12 | |
2022-10-23 | non-implemented mask with any type | Stephen | -2/+6 | |
2022-10-23 | [API][Feature] - Add img2img API endpoint | Stephen | -8/+63 | |
2022-10-23 | Update hypernetwork.py | DepFA | -4/+7 | |
2022-10-22 | Add "extra" single image operation | Bruno Seoane | -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 | ||||
2022-10-22 | Moved moodels to their own file and extracted base64 conversion to its own ↵ | Bruno Seoane | -11/+14 | |
function | ||||
2022-10-22 | Remove unused imports | Bruno Seoane | -4/+1 | |
2022-10-22 | Allow tracking real-time loss | AngelBottomless | -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. | ||||
2022-10-22 | fix for img2img color correction in a batch #3218 | AUTOMATIC | -2/+4 | |
2022-10-22 | add --freeze-settings commandline argument to disable changing settings | AUTOMATIC | -2/+10 | |
2022-10-22 | removed the option to use 2x more memory when generating previews | AUTOMATIC | -29/+14 | |
added an option to always only show one image in previews removed duplicate code | ||||
2022-10-22 | Generate grid preview for progress image | Unnoen | -2/+30 | |
2022-10-22 | Update hypernetwork.py | AngelBottomless | -11/+44 | |
2022-10-22 | call model_loaded_callback after setting shared.sd_model in case scripts ↵ | AUTOMATIC | -1/+2 | |
refer to it using that | ||||
2022-10-22 | fix aesthetic gradients doing nothing after loading a different model | MrCheeze | -2/+2 | |
2022-10-22 | record First pass size as 0x0 for #3328 | AUTOMATIC | -1/+2 | |
2022-10-22 | Merge pull request #3414 from discus0434/master | AUTOMATIC1111 | -40/+63 | |
[Hypernetworks] Add a feature to use dropout / more activation functions | ||||
2022-10-22 | fix part2 | Greendayle | -1/+1 | |
2022-10-22 | Deepdanbooru linux fix | Greendayle | -1/+2 | |
2022-10-22 | typo | AUTOMATIC | -1/+1 | |
2022-10-22 | added callback for creating new settings in extensions | AUTOMATIC | -3/+33 | |
2022-10-22 | small fix | discus0434 | -4/+3 | |
2022-10-22 | Merge branch 'AUTOMATIC1111:master' into master | discus0434 | -0/+14 | |
2022-10-22 | small fix | discus0434 | -8/+5 | |
2022-10-22 | add an option to avoid dying relu | discus0434 | -6/+6 | |
2022-10-22 | added a guard for hypernet training that will stop early if weights are ↵ | AUTOMATIC | -0/+11 | |
getting no gradients | ||||
2022-10-22 | fix for extensions without style.css | AUTOMATIC | -0/+3 | |
2022-10-22 | Merge branch 'master' of upstream | discus0434 | -354/+1360 | |
2022-10-22 | add dropout | discus0434 | -51/+70 | |
2022-10-22 | remove parsing command line from devices.py | AUTOMATIC | -14/+9 | |
2022-10-22 | Merge branch 'master' into cuda-device-id-selection | AUTOMATIC1111 | -552/+667 | |
2022-10-22 | further support for extensions | AUTOMATIC | -18/+45 | |
2022-10-22 | removed aesthetic gradients as built-in | AUTOMATIC | -406/+244 | |
added support for extensions | ||||
2022-10-22 | implement CUDA device selection, --device-id arg | Extraltodeus | -0/+1 | |
2022-10-22 | implement CUDA device selection by ID | Extraltodeus | -3/+18 | |
2022-10-21 | Merge remote-tracking branch 'historytab/master' | AUTOMATIC | -133/+383 | |
2022-10-21 | prevent error spam when processing images without txt files for captions | AUTOMATIC | -5/+4 | |
2022-10-21 | Merge branch 'master' into fix/train-preprocess-keep-ratio | AUTOMATIC1111 | -112/+976 | |
2022-10-21 | loading SD VAE, see PR #3303 | AUTOMATIC | -1/+4 | |
2022-10-21 | make aspect ratio overlay work regardless of selected localization | AUTOMATIC | -2/+2 | |
2022-10-21 | Change option description of unload_models_when_training | Rcmcpe | -1/+1 | |
2022-10-21 | Remove unused variable. | timntorres | -1/+0 | |
2022-10-21 | Refer to Hypernet's name, sensibly, by its name variable. | timntorres | -1/+1 | |