aboutsummaryrefslogtreecommitdiffstats
path: root/webui.py
Commit message (Collapse)AuthorAgeFilesLines
* remove unwanted formatting/functionality from the PRAUTOMATIC2022-09-301-1/+1
|
* Merge remote-tracking branch 'upstream/master' into ModelLoaderd8ahazard2022-09-301-0/+8
|\
| * call torch_gc before/after each gpu gradio operationAUTOMATIC2022-09-291-0/+5
| |
* | Holy $hit.d8ahazard2022-09-291-6/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Yep. Fix gfpgan_model_arch requirement(s). Add Upscaler base class, move from images. Add a lot of methods to Upscaler. Re-work all the child upscalers to be proper classes. Add BSRGAN scaler. Add ldsr_model_arch class, removing the dependency for another repo that just uses regular latent-diffusion stuff. Add one universal method that will always find and load new upscaler models without having to add new "setup_model" calls. Still need to add command line params, but that could probably be automated. Add a "self.scale" property to all Upscalers so the scalers themselves can do "things" in response to the requested upscaling size. Ensure LDSR doesn't get stuck in a longer loop of "upscale/downscale/upscale" as we try to reach the target upscale size. Add typehints for IDE sanity. PEP-8 improvements. Moar.
* | Merge remote-tracking branch 'upstream/master' into ModelLoaderd8ahazard2022-09-271-1/+2
|\|
| * Add support for checkpoint mergingWilliam Moorehouse2022-09-251-1/+2
| |
* | Use model loader with stable-diffusion too.d8ahazard2022-09-271-0/+1
| | | | | | | | | | | | | | | | | | | | Hook the model loader into the SD_models file. Add default url/download if checkpoint is not found. Add matching stablediffusion-models-path argument. Add message that --ckpt-dir will be removed in the future, but have it pipe to stablediffusion-models-path for now. Update help strings for models-path args so they're more or less uniform. Move sd_model "setup" call to webUI with the others. Ensure "cleanup_models" method moves existing models to the new locations, including SD, and that we aren't deleting folders that still have stuff in them.
* | Cleanup existing directories, fixesd8ahazard2022-09-261-0/+2
| |
* | Re-implement universal model loadingd8ahazard2022-09-261-24/+21
|/
* Changed job_id to timestampEyrie2022-09-251-1/+1
|
* Added job_id pattern for directoriesEyrie2022-09-251-0/+1
|
* prevent weird behavior when pressing interrupt just as image finishesAUTOMATIC2022-09-231-0/+1
|
* Add LDSR and "GoLatent?" Upscaling (#763)d8ahazard2022-09-211-1/+2
| | | * Add LDSR Upscaling
* Update webui.pyC43H66N12O12S22022-09-201-1/+1
|
* add swinir importC43H66N12O12S22022-09-201-0/+1
|
* hackC43H66N12O12S22022-09-201-0/+1
|
* added command line argument --autolaunch to open the webui URL in the ↵Connum2022-09-181-0/+1
| | | | system's default browser upon launch (implements #274)
* add support for switching model checkpoints at runtimeAUTOMATIC2022-09-171-51/+10
|
* Include the model name (or the SHA256 of the file) in the metadata #271AUTOMATIC2022-09-121-1/+9
|
* aaaaaaaaaaaaaaaaaAUTOMATIC2022-09-121-1/+1
|
* rename --channelslast to --opt-channelslast to be in line with other torch ↵AUTOMATIC2022-09-121-1/+1
| | | | optimizations
* webui.py channels last supportC43H66N12O12S22022-09-121-1/+2
|
* fixed gradio auth bug in PRAUTOMATIC2022-09-121-1/+1
|
* Merge branch 'master' into masterEyeDeck2022-09-121-2/+7
|\
| * [Feature Request] Please add "--share-password" for Gradio server security #315AUTOMATIC2022-09-121-1/+7
| |
* | Add --auth command line argument to enable Gradio authenticationEyeDeck2022-09-121-1/+2
|/ | | | | | | Allows you to pass in Gradio authentication like: `--auth username:password` Supports multiple sets of credentials by comma-delimiting, like: `--auth user1:pass1,user2:pass3`...
* --gradio-debug for collab usersAUTOMATIC2022-09-121-1/+1
|
* CLIP interrogatorAUTOMATIC2022-09-111-1/+3
|
* [Feature Request] Save defaults for extras & keep image parameters after ↵AUTOMATIC2022-09-111-81/+4
| | | | using extras #251
* fix aggressive caching for extras tabAUTOMATIC2022-09-081-1/+1
|
* honor tiling settings for RealESRGAN alsoAUTOMATIC2022-09-081-3/+1
| | | | load scripts earlier to get errors before model loads
* add webui() function for more simple cell in the notebookAUTOMATIC2022-09-081-2/+7
|
* fix defaultorionaskatu2022-09-081-1/+1
|
* Port defaults to noneorionaskatu2022-09-081-1/+1
|
* Add server_port param to webui.pyorionaskatu2022-09-081-1/+1
|
* a little bit of rework for extras tabAUTOMATIC2022-09-071-5/+14
|
* codeformer supportAUTOMATIC2022-09-071-8/+12
|
* fix for live progress breaking lowvram and medvram optimizationsAUTOMATIC2022-09-061-1/+1
|
* fix for progress barAUTOMATIC2022-09-061-0/+1
|
* added preview optionAUTOMATIC2022-09-061-2/+3
|
* readme extras for VRAM forAUTOMATIC2022-09-061-1/+1
| | | | | | added missing packages to requirements for #74 add support for negative numbers in X/Y plot (plus ranges) #73 changed progressbar to work properly with custom modes
* allow import as library for #72AUTOMATIC2022-09-061-13/+13
|
* added progressbarAUTOMATIC2022-09-051-0/+7
| | | | | added an option to disable progressbar added interrupt support to DDIM/PLMS
* added --listen option to make gradio listen on network requestsAUTOMATIC2022-09-051-1/+1
|
* re-integrated tiling option as a UI elementAUTOMATIC2022-09-051-5/+0
|
* add an option to enable tiling image generationAUTOMATIC2022-09-041-0/+5
|
* ESRGAN supportAUTOMATIC2022-09-041-12/+31
|
* Fixed typo 'medram' -> 'medvram' in webui.pyhentailord85ez2022-09-031-1/+1
|
* support for scriptsAUTOMATIC2022-09-031-22/+4
|
* split codebase into multiple files; to anyone this affects negatively: sorryAUTOMATIC2022-09-031-2032/+55
|
generated by cgit v1.2.3 (git 2.25.1) at 2025-04-29 23:50:02 +0000