Commit message (Collapse) | Author | Age | Files | Lines | |
---|---|---|---|---|---|
* | add sampler_noise_scheduler_override switch | DepFA | 2022-10-01 | 1 | -2/+8 |
| | |||||
* | add sampler_noise_scheduler_override property | DepFA | 2022-10-01 | 1 | -2/+2 |
| | |||||
* | ALT + return will submit prompt when it's in focus | Trung Ngo | 2022-09-30 | 1 | -1/+1 |
| | |||||
* | remove extra print from BSRGAN | AUTOMATIC | 2022-09-30 | 1 | -1/+0 |
| | |||||
* | Merge pull request #1371 from d8ahazard/master | AUTOMATIC1111 | 2022-09-30 | 4 | -7/+17 |
|\ | | | | | Fix LDSR, BSRGAN, recursive SD checkpoint Loading | ||||
| * | Merge branch 'master' into master | d8ahazard | 2022-09-30 | 2 | -2/+3 |
| |\ | |||||
| * | | Update bsrgan_model.py | d8ahazard | 2022-09-30 | 1 | -1/+0 |
| | | | |||||
| * | | Merge branch 'master' of https://github.com/d8ahazard/stable-diffusion-webui | d8ahazard | 2022-09-30 | 4 | -11/+18 |
| |\ \ | |||||
| | * \ | Merge branch 'master' into master | d8ahazard | 2022-09-30 | 4 | -11/+18 |
| | |\ \ | |||||
| * | | | | Fix BSRGAN Model loading. | d8ahazard | 2022-09-30 | 1 | -1/+2 |
| |/ / / | |||||
| * | | | Set default value for ckpt-dir | d8ahazard | 2022-09-30 | 1 | -1/+1 |
| | | | | |||||
| * | | | Remove unused LDSR opt | d8ahazard | 2022-09-30 | 1 | -1/+0 |
| | | | | |||||
| * | | | Logging.... | d8ahazard | 2022-09-30 | 1 | -1/+0 |
| | | | | | | | | | | | | | | | | Cleanup. Sorry. | ||||
| * | | | Fix recursive model loading | d8ahazard | 2022-09-30 | 1 | -1/+3 |
| | | | | | | | | | | | | | | | | Ensure we find checkpoints within subdirectories. | ||||
| * | | | Fix BSRGAN variable not found. | d8ahazard | 2022-09-30 | 1 | -2/+1 |
| | | | | |||||
| * | | | Remove useless print message | d8ahazard | 2022-09-30 | 1 | -1/+0 |
| | | | | |||||
| * | | | Fix model paths, ensure we have the right files. | d8ahazard | 2022-09-30 | 2 | -4/+8 |
| | | | | | | | | | | | | | | | | Also, clean up logging in the ldsr arch file. | ||||
| * | | | Remove LDSR project.yaml if too large. | d8ahazard | 2022-09-30 | 1 | -0/+7 |
| | | | | | | | | | | | | | | | | If we accidentally downloaded the wrong file and saved it as project.yaml, this will delete it so it can be re-downloaded. | ||||
| * | | | Fix LDSR YAML path | d8ahazard | 2022-09-30 | 1 | -1/+1 |
| | | | | |||||
* | | | | fix model checkpoint merger tab failing to save model | AUTOMATIC | 2022-09-30 | 1 | -1/+3 |
| |_|/ |/| | | |||||
* | | | if --ckpt option is specified, load that model | AUTOMATIC | 2022-09-30 | 2 | -1/+2 |
| |/ |/| | |||||
* | | Merge remote-tracking branch 'origin/master' | AUTOMATIC | 2022-09-30 | 2 | -1/+17 |
|\| | |||||
| * | fixed so that {prompt} can be anywhere in style | RnDMonkey | 2022-09-30 | 1 | -1/+5 |
| | | |||||
| * | refined [styles] pattern and added [prompt_no_styles] | RnDMonkey | 2022-09-30 | 2 | -1/+13 |
| | | |||||
* | | hello #1109 | AUTOMATIC | 2022-09-30 | 1 | -1/+1 |
| | | |||||
* | | fix for one error with BSRGAN, though it fails to work anyway #1109 | AUTOMATIC | 2022-09-30 | 1 | -2/+1 |
| | | |||||
* | | change default inpaint mode to original | AUTOMATIC | 2022-09-30 | 1 | -1/+1 |
| | | |||||
* | | prevent neural network resizing when it is not necessary #1109 | AUTOMATIC | 2022-09-30 | 1 | -8/+10 |
| | | |||||
* | | add embeddings dir | AUTOMATIC | 2022-09-30 | 1 | -1/+6 |
|/ | |||||
* | return the dropdown that mysteriously disappeared | AUTOMATIC | 2022-09-30 | 1 | -1/+1 |
| | |||||
* | repair broken highres fix #1109 | AUTOMATIC | 2022-09-30 | 2 | -3/+2 |
| | |||||
* | revert the annotation not supported by old pythons | AUTOMATIC | 2022-09-30 | 1 | -1/+1 |
| | |||||
* | remove unwanted formatting/functionality from the PR | AUTOMATIC | 2022-09-30 | 9 | -168/+125 |
| | |||||
* | fix for broken codeformer in PR | AUTOMATIC | 2022-09-30 | 1 | -1/+1 |
| | |||||
* | undo upscaler model filename tampering | AUTOMATIC | 2022-09-30 | 1 | -1/+0 |
| | |||||
* | fix the bug with broken rescaling in PR | AUTOMATIC | 2022-09-30 | 2 | -4/+12 |
| | |||||
* | fix bugs in the PR | AUTOMATIC | 2022-09-30 | 2 | -2/+2 |
| | |||||
* | Merge pull request #1109 from d8ahazard/ModelLoader | AUTOMATIC1111 | 2022-09-30 | 18 | -1385/+2145 |
|\ | | | | | Model Loader, Fixes | ||||
| * | Fixes, cleanup. | d8ahazard | 2022-09-30 | 3 | -17/+5 |
| | | |||||
| * | Merge remote-tracking branch 'upstream/master' into ModelLoader | d8ahazard | 2022-09-30 | 11 | -133/+483 |
| |\ | |||||
| * | | Holy $hit. | d8ahazard | 2022-09-29 | 16 | -639/+1009 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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. | ||||
| * | | Remove debugging message | d8ahazard | 2022-09-27 | 1 | -1/+0 |
| | | | |||||
| * | | Merge remote-tracking branch 'upstream/master' into ModelLoader | d8ahazard | 2022-09-27 | 5 | -13/+140 |
| |\ \ | |||||
| * | | | Use model loader with stable-diffusion too. | d8ahazard | 2022-09-27 | 3 | -37/+64 |
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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, fixes | d8ahazard | 2022-09-26 | 4 | -14/+45 |
| | | | | |||||
| * | | | Re-implement universal model loading | d8ahazard | 2022-09-26 | 11 | -104/+422 |
| | | | | |||||
| * | | | Rename swinir -> swinir_model | d8ahazard | 2022-09-26 | 1 | -123/+123 |
| | | | | |||||
| * | | | Fix swinir arch name | d8ahazard | 2022-09-26 | 1 | -867/+867 |
| | | | | |||||
* | | | | fix the sys not found error when importing sd_samplers that appeared after PR | AUTOMATIC | 2022-09-30 | 2 | -10/+11 |
| | | | | |||||
* | | | | force usage of cloned k-diffusion | C43H66N12O12S2 | 2022-09-30 | 1 | -1/+2 |
| | | | |