Age | Commit message (Collapse) | Author | |
---|---|---|---|
2022-09-30 | remove unwanted formatting/functionality from the PR | AUTOMATIC | |
2022-09-29 | Merge remote-tracking branch 'upstream/master' into ModelLoader | d8ahazard | |
2022-09-29 | Holy $hit. | d8ahazard | |
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. | |||
2022-09-29 | call torch_gc before/after each gpu gradio operation | AUTOMATIC | |
2022-09-27 | Merge remote-tracking branch 'upstream/master' into ModelLoader | d8ahazard | |
2022-09-27 | Use model loader with stable-diffusion too. | d8ahazard | |
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. | |||
2022-09-26 | Cleanup existing directories, fixes | d8ahazard | |
2022-09-26 | Re-implement universal model loading | d8ahazard | |
2022-09-25 | Add support for checkpoint merging | William Moorehouse | |
2022-09-25 | Changed job_id to timestamp | Eyrie | |
2022-09-25 | Added job_id pattern for directories | Eyrie | |
2022-09-23 | prevent weird behavior when pressing interrupt just as image finishes | AUTOMATIC | |
2022-09-21 | Add LDSR and "GoLatent?" Upscaling (#763) | d8ahazard | |
* Add LDSR Upscaling | |||
2022-09-20 | Update webui.py | C43H66N12O12S2 | |
2022-09-20 | add swinir import | C43H66N12O12S2 | |
2022-09-20 | hack | C43H66N12O12S2 | |
2022-09-18 | added command line argument --autolaunch to open the webui URL in the ↵ | Connum | |
system's default browser upon launch (implements #274) | |||
2022-09-17 | add support for switching model checkpoints at runtime | AUTOMATIC | |
2022-09-12 | Include the model name (or the SHA256 of the file) in the metadata #271 | AUTOMATIC | |
2022-09-12 | aaaaaaaaaaaaaaaaa | AUTOMATIC | |
2022-09-12 | rename --channelslast to --opt-channelslast to be in line with other torch ↵ | AUTOMATIC | |
optimizations | |||
2022-09-12 | webui.py channels last support | C43H66N12O12S2 | |
2022-09-12 | fixed gradio auth bug in PR | AUTOMATIC | |
2022-09-12 | Merge branch 'master' into master | EyeDeck | |
2022-09-12 | [Feature Request] Please add "--share-password" for Gradio server security #315 | AUTOMATIC | |
2022-09-12 | Add --auth command line argument to enable Gradio authentication | EyeDeck | |
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`... | |||
2022-09-12 | --gradio-debug for collab users | AUTOMATIC | |
2022-09-11 | CLIP interrogator | AUTOMATIC | |
2022-09-11 | [Feature Request] Save defaults for extras & keep image parameters after ↵ | AUTOMATIC | |
using extras #251 | |||
2022-09-08 | fix aggressive caching for extras tab | AUTOMATIC | |
2022-09-08 | honor tiling settings for RealESRGAN also | AUTOMATIC | |
load scripts earlier to get errors before model loads | |||
2022-09-08 | add webui() function for more simple cell in the notebook | AUTOMATIC | |
2022-09-08 | fix default | orionaskatu | |
2022-09-08 | Port defaults to none | orionaskatu | |
2022-09-08 | Add server_port param to webui.py | orionaskatu | |
2022-09-07 | a little bit of rework for extras tab | AUTOMATIC | |
2022-09-07 | codeformer support | AUTOMATIC | |
2022-09-06 | fix for live progress breaking lowvram and medvram optimizations | AUTOMATIC | |
2022-09-06 | fix for progress bar | AUTOMATIC | |
2022-09-06 | added preview option | AUTOMATIC | |
2022-09-06 | readme extras for VRAM for | AUTOMATIC | |
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 | |||
2022-09-06 | allow import as library for #72 | AUTOMATIC | |
2022-09-06 | added progressbar | AUTOMATIC | |
added an option to disable progressbar added interrupt support to DDIM/PLMS | |||
2022-09-05 | added --listen option to make gradio listen on network requests | AUTOMATIC | |
2022-09-05 | re-integrated tiling option as a UI element | AUTOMATIC | |
2022-09-05 | add an option to enable tiling image generation | AUTOMATIC | |
2022-09-04 | ESRGAN support | AUTOMATIC | |
2022-09-03 | Fixed typo 'medram' -> 'medvram' in webui.py | hentailord85ez | |
2022-09-03 | support for scripts | AUTOMATIC | |
2022-09-03 | split codebase into multiple files; to anyone this affects negatively: sorry | AUTOMATIC | |