aboutsummaryrefslogtreecommitdiffstats
path: root/modules
Commit message (Collapse)AuthorAgeFilesLines
...
| * | | | prevent neural network resizing when it is not necessary #1109AUTOMATIC2022-09-301-8/+10
| | | | |
| * | | | add embeddings dirAUTOMATIC2022-09-301-1/+6
| |/ / /
| * | | return the dropdown that mysteriously disappearedAUTOMATIC2022-09-301-1/+1
| | | |
| * | | repair broken highres fix #1109AUTOMATIC2022-09-302-3/+2
| | | |
| * | | revert the annotation not supported by old pythonsAUTOMATIC2022-09-301-1/+1
| | | |
| * | | remove unwanted formatting/functionality from the PRAUTOMATIC2022-09-309-168/+125
| | | |
| * | | fix for broken codeformer in PRAUTOMATIC2022-09-301-1/+1
| | | |
| * | | undo upscaler model filename tamperingAUTOMATIC2022-09-301-1/+0
| | | |
| * | | fix the bug with broken rescaling in PRAUTOMATIC2022-09-302-4/+12
| | | |
| * | | fix bugs in the PRAUTOMATIC2022-09-302-2/+2
| | | |
| * | | Merge pull request #1109 from d8ahazard/ModelLoaderAUTOMATIC11112022-09-3018-1385/+2145
| |\ \ \ | | | | | | | | | | Model Loader, Fixes
| | * | | Fixes, cleanup.d8ahazard2022-09-303-17/+5
| | | | |
| | * | | Merge remote-tracking branch 'upstream/master' into ModelLoaderd8ahazard2022-09-3011-133/+483
| | |\ \ \
| | * | | | Holy $hit.d8ahazard2022-09-2916-639/+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 messaged8ahazard2022-09-271-1/+0
| | | | | |
| | * | | | Merge remote-tracking branch 'upstream/master' into ModelLoaderd8ahazard2022-09-275-13/+140
| | |\ \ \ \
| | * | | | | Use model loader with stable-diffusion too.d8ahazard2022-09-273-37/+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, fixesd8ahazard2022-09-264-14/+45
| | | | | | |
| | * | | | | Re-implement universal model loadingd8ahazard2022-09-2611-104/+422
| | | | | | |
| | * | | | | Rename swinir -> swinir_modeld8ahazard2022-09-261-123/+123
| | | | | | |
| | * | | | | Fix swinir arch named8ahazard2022-09-261-867/+867
| | | | | | |
| * | | | | | fix the sys not found error when importing sd_samplers that appeared after PRAUTOMATIC2022-09-302-10/+11
| | | | | | |
| * | | | | | force usage of cloned k-diffusionC43H66N12O12S22022-09-301-1/+2
| | | | | | |
| * | | | | | return shortest checkpoint title matchDepFA2022-09-301-11/+1
| | | | | | |
| * | | | | | add get_closet_checkpoint_matchDepFA2022-09-301-0/+15
| | |_|/ / / | |/| | | |
| * | | | | Save parameters as comments when saving as jpgJustin Maier2022-09-291-5/+14
| | | | | |
| * | | | | Save should use desired sample format fixes #1028Justin Maier2022-09-291-1/+1
| | | | | |
| * | | | | fix for incorrect model weight loading for #814AUTOMATIC2022-09-292-1/+14
| | | | | |
| * | | | | improve code qualityC43H66N12O12S22022-09-291-9/+7
| | | | | |
| * | | | | add new samplersC43H66N12O12S22022-09-291-1/+10
| | |_|_|/ | |/| | |
| * | | | drop the printHanusz Leszek2022-09-291-1/+0
| | | | |
| * | | | Sort scripts loading orderHanusz Leszek2022-09-291-1/+2
| | | | |
| * | | | Add custom name and try-exceptsafentisAuth2022-09-292-2/+15
| | | | |
| * | | | Add output folder iconsMichoko2022-09-291-3/+3
| | | | | | | | | | | | | | | | | | | | Changed the hidden element class name to a more generic one, so people can reuse it if they want to hide further elements in the future
| * | | | Add output folder iconsMichoko2022-09-291-4/+16
| | | | | | | | | | | | | | | | | | | | Handling of the --hide-ui-dir-config flag and added multi-platform code for opening a folder
| * | | | Add output folder iconsMichoko2022-09-291-1/+25
| | | | | | | | | | | | | | | | | | | | Adds icons on the first 3 tabs to directly open the corresponding images output directory
| * | | | fix program breaking on empty promptAUTOMATIC2022-09-291-0/+3
| | | | |
| * | | | new implementation for attention/emphasisAUTOMATIC2022-09-293-6/+186
| | | | |
| * | | | remove unneded debug printAUTOMATIC2022-09-291-1/+0
| | | | |
* | | | | Move silu to sd_hijackJairo Correa2022-09-291-9/+3
| | | | |
* | | | | Fix memory leak and reduce memory usageJairo Correa2022-09-295-16/+39
|/ / / /
* | | | Respect --ckpt-dir command-line argument when merging models (#1261)William Moorehouse2022-09-281-1/+1
| | | | | | | | | | | | | | | | * Update .gitignore to ignore *all* checkpoint files in /models * Fixed typo in UI
* | | | update lists of models after merging them in checkpoints tabAUTOMATIC2022-09-284-34/+52
| | | | | | | | | | | | | | | | support saving as half
* | | | correctly list and display model names for #1261AUTOMATIC2022-09-282-17/+10
| | | |
* | | | fix broken DDIM with img2imgAUTOMATIC2022-09-281-2/+2
| | | |
* | | | clone k-diffusion instead of installing it via pip, and do not install its ↵AUTOMATIC2022-09-281-0/+1
| | | | | | | | | | | | | | | | requirements.txt
* | | | Merge pull request #1194 from liamkerr/token_countAUTOMATIC11112022-09-282-9/+30
|\ \ \ \ | | | | | | | | | | Token count
| * | | | removed unused import; now using javascript to watch prompt textareaLiam2022-09-281-2/+0
| | | | |
| * | | | switched the token counter to use hidden buttons instead of api callLiam2022-09-272-6/+10
| | | | |
| * | | | Merge remote-tracking branch 'upstream/master' into token_countLiam2022-09-276-22/+153
| |\ \ \ \