aboutsummaryrefslogtreecommitdiffstats
path: root/modules/extras.py
AgeCommit message (Collapse)AuthorLines
2022-12-24fix(api): don't save extras output to diskPhilpax-8/+9
2022-12-24Merge pull request #5747 from yuvalabou/singleton-comparisonAUTOMATIC1111-1/+1
Format singleton comparisons
2022-12-24Merge pull request #5814 from timntorres/5802-save-upscaler-to-filenameAUTOMATIC1111-1/+7
Add option to save upscaler to filename suffix in extras tab.
2022-12-17Add option to include upscaler name in filename.timntorres-2/+3
2022-12-17Add upscaler name as a suffix.timntorres-1/+6
2022-12-14Correct singleton comparisonsYuval Aboulafia-1/+1
2022-12-04extras.py: use as little RAM as possible, misc fixesMackerel-18/+19
maximum of 2 models loaded at once. delete unneeded model before next step. fix 'teritary' -> 'tertiary'. gracefully fail when "add difference" is selected without a tertiary model
2022-12-04make it possible to merge inpainting model with non-inpainting oneAUTOMATIC-2/+25
2022-11-27rework #5012 to also work for pictures dragged into the prompt and also add ↵AUTOMATIC-35/+5
Clip skip + ENSD to parameters
2022-11-27Merge pull request #5012 from Nandaka/masterAUTOMATIC1111-0/+14
Support NAI style exif in PNG Info for Send... buttons
2022-11-27add safetensors support for model merging #4869AUTOMATIC-12/+14
2022-11-24Support NAI exif for PNG InfoNandaka-0/+14
2022-11-02extras - skip unnecessary second hash of imageChris OBryan-2/+3
There is no need to re-hash the input image each iteration of the loop. This also reverts PR #4026 as it was determined the cache hits it avoids were actually valid.
2022-10-31Extend extras image cache with upscale_first argDepFA-1/+1
2022-10-29skip filenames starting with . for img2img and extras batch modesAUTOMATIC-1/+1
2022-10-28extras: upscaler blending should not be considered in cache keyChris OBryan-1/+1
2022-10-28extras-tweaks: autoformat changed linesChris OBryan-15/+15
2022-10-28extras: Make image cache LRUChris OBryan-29/+38
This changes the extras image cache into a Least-Recently-Used cache. This allows more experimentation with different upscalers without missing the cache. Max cache size is increased to 5 and is cleared on source image update.
2022-10-28extras: Rework image cacheChris OBryan-20/+32
Bit of a refactor to the image cache to make it easier to extend. Also takes into account the entire image instead of just a cropped portion.
2022-10-28extras: Add option to run upscaling before face fixingChris OBryan-50/+95
Face restoration can look much better if ran after upscaling, as it allows the restoration to fix upscaling artifacts. This patch adds an option to choose which order to run upscaling/face fixing in.
2022-10-21sort file list in alphabetical ordering in extraswinterspringsummer-1/+1
2022-10-21Fixed path issue while extras batch processingwinterspringsummer-3/+3
2022-10-21Added try except to extras batch from directorywinterspringsummer-4/+7
2022-10-21Fixed path issue while extras batch processingwinterspringsummer-4/+8
2022-10-18additional fix for difference model mergingAUTOMATIC-1/+1
2022-10-18fix for add difference model mergingAUTOMATIC-2/+5
2022-10-18extras extend cache key with new upscale to optionsDepFA-1/+2
2022-10-17fix bug for latest model merge RAM improvementAUTOMATIC-0/+1
2022-10-17improve performance of 3-way merge on machines with not enough ram, by only ↵MrCheeze-10/+17
accessing two of the models at a time
2022-10-16honor --hide-ui-dir-config option for #2807AUTOMATIC-0/+2
2022-10-16added extras batch work from directorywinterspringsummer-5/+18
2022-10-14change checkpoint merger to work in a more obvious wayAUTOMATIC-19/+5
remove sigmoid and inverse sigmoid because they just did the same thing as weighed sum only with changed multiplier
2022-10-14should fix the issue with missing layers in chechpoint mergerAUTOMATIC-1/+6
2022-10-14add an ability to merge three checkpointsAUTOMATIC-8/+21
2022-10-10Simplify crop logicJustin Maier-11/+3
2022-10-09Add "Scale to" option to ExtrasJustin Maier-5/+23
2022-10-09fix missing png info when Extras Batch ProcessArtem Zagidulin-1/+1
2022-10-09additional changes for saving pnginfo for #1803AUTOMATIC-0/+4
2022-10-09make main model loading and model merger use the same codeAUTOMATIC-3/+3
2022-09-30Merge branch 'master' into fix-vramJairo Correa-3/+8
2022-09-30fix model checkpoint merger tab failing to save modelAUTOMATIC-1/+3
2022-09-30remove unwanted formatting/functionality from the PRAUTOMATIC-17/+18
2022-09-29Merge remote-tracking branch 'upstream/master' into ModelLoaderd8ahazard-23/+31
2022-09-29Holy $hit.d8ahazard-18/+17
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.
2022-09-29Add custom name and try-exceptsafentisAuth-1/+2
2022-09-28Fix memory leak and reduce memory usageJairo Correa-0/+2
2022-09-29update lists of models after merging them in checkpoints tabAUTOMATIC-10/+17
support saving as half
2022-09-29correctly list and display model names for #1261AUTOMATIC-15/+8
2022-09-28Adding support for inverse sigmoid interpolationBernard Maltais-0/+7
2022-09-27-Fix interp_amount rounding in filenameBernard Maltais-2/+2
-Sort list of checkpoints in list
generated by cgit v1.2.3 (git 2.39.1) at 2025-10-14 21:26:36 +0000