| Commit message (Collapse) | Author | Age | Files | Lines | |
|---|---|---|---|---|---|
| * | fix(api): don't save extras output to disk | Philpax | 2022-12-24 | 1 | -8/+9 |
| | | |||||
| * | Merge pull request #5747 from yuvalabou/singleton-comparison | AUTOMATIC1111 | 2022-12-24 | 1 | -1/+1 |
| |\ | | | | | Format singleton comparisons | ||||
| | * | Correct singleton comparisons | Yuval Aboulafia | 2022-12-14 | 1 | -1/+1 |
| | | | |||||
| * | | Merge pull request #5814 from timntorres/5802-save-upscaler-to-filename | AUTOMATIC1111 | 2022-12-24 | 1 | -1/+7 |
| |\ \ | |/ |/| | Add option to save upscaler to filename suffix in extras tab. | ||||
| | * | Add option to include upscaler name in filename. | timntorres | 2022-12-17 | 1 | -2/+3 |
| | | | |||||
| | * | Add upscaler name as a suffix. | timntorres | 2022-12-17 | 1 | -1/+6 |
| | | | |||||
| * | | extras.py: use as little RAM as possible, misc fixes | Mackerel | 2022-12-04 | 1 | -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 | ||||
| * | make it possible to merge inpainting model with non-inpainting one | AUTOMATIC | 2022-12-04 | 1 | -2/+25 |
| | | |||||
| * | rework #5012 to also work for pictures dragged into the prompt and also add ↵ | AUTOMATIC | 2022-11-27 | 1 | -35/+5 |
| | | | | | Clip skip + ENSD to parameters | ||||
| * | Merge pull request #5012 from Nandaka/master | AUTOMATIC1111 | 2022-11-27 | 1 | -0/+14 |
| |\ | | | | | Support NAI style exif in PNG Info for Send... buttons | ||||
| | * | Support NAI exif for PNG Info | Nandaka | 2022-11-24 | 1 | -0/+14 |
| | | | |||||
| * | | add safetensors support for model merging #4869 | AUTOMATIC | 2022-11-27 | 1 | -12/+14 |
| |/ | |||||
| * | extras - skip unnecessary second hash of image | Chris OBryan | 2022-11-03 | 1 | -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. | ||||
| * | Extend extras image cache with upscale_first arg | DepFA | 2022-10-31 | 1 | -1/+1 |
| | | |||||
| * | skip filenames starting with . for img2img and extras batch modes | AUTOMATIC | 2022-10-29 | 1 | -1/+1 |
| | | |||||
| * | extras: upscaler blending should not be considered in cache key | Chris OBryan | 2022-10-28 | 1 | -1/+1 |
| | | |||||
| * | extras-tweaks: autoformat changed lines | Chris OBryan | 2022-10-28 | 1 | -15/+15 |
| | | |||||
| * | extras: Make image cache LRU | Chris OBryan | 2022-10-28 | 1 | -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. | ||||
| * | extras: Rework image cache | Chris OBryan | 2022-10-28 | 1 | -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. | ||||
| * | extras: Add option to run upscaling before face fixing | Chris OBryan | 2022-10-28 | 1 | -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. | ||||
| * | sort file list in alphabetical ordering in extras | winterspringsummer | 2022-10-21 | 1 | -1/+1 |
| | | |||||
| * | Fixed path issue while extras batch processing | winterspringsummer | 2022-10-21 | 1 | -3/+3 |
| | | |||||
| * | Added try except to extras batch from directory | winterspringsummer | 2022-10-21 | 1 | -4/+7 |
| | | |||||
| * | Fixed path issue while extras batch processing | winterspringsummer | 2022-10-21 | 1 | -4/+8 |
| | | |||||
| * | additional fix for difference model merging | AUTOMATIC | 2022-10-18 | 1 | -1/+1 |
| | | |||||
| * | fix for add difference model merging | AUTOMATIC | 2022-10-18 | 1 | -2/+5 |
| | | |||||
| * | extras extend cache key with new upscale to options | DepFA | 2022-10-18 | 1 | -1/+2 |
| | | |||||
| * | fix bug for latest model merge RAM improvement | AUTOMATIC | 2022-10-17 | 1 | -0/+1 |
| | | |||||
| * | improve performance of 3-way merge on machines with not enough ram, by only ↵ | MrCheeze | 2022-10-17 | 1 | -10/+17 |
| | | | | | accessing two of the models at a time | ||||
| * | honor --hide-ui-dir-config option for #2807 | AUTOMATIC | 2022-10-16 | 1 | -0/+2 |
| | | |||||
| * | added extras batch work from directory | winterspringsummer | 2022-10-16 | 1 | -5/+18 |
| | | |||||
| * | change checkpoint merger to work in a more obvious way | AUTOMATIC | 2022-10-14 | 1 | -19/+5 |
| | | | | | remove sigmoid and inverse sigmoid because they just did the same thing as weighed sum only with changed multiplier | ||||
| * | should fix the issue with missing layers in chechpoint merger | AUTOMATIC | 2022-10-14 | 1 | -1/+6 |
| | | |||||
| * | add an ability to merge three checkpoints | AUTOMATIC | 2022-10-14 | 1 | -8/+21 |
| | | |||||
| * | Simplify crop logic | Justin Maier | 2022-10-10 | 1 | -11/+3 |
| | | |||||
| * | Add "Scale to" option to Extras | Justin Maier | 2022-10-10 | 1 | -5/+23 |
| | | |||||
| * | fix missing png info when Extras Batch Process | Artem Zagidulin | 2022-10-09 | 1 | -1/+1 |
| | | |||||
| * | additional changes for saving pnginfo for #1803 | AUTOMATIC | 2022-10-09 | 1 | -0/+4 |
| | | |||||
| * | make main model loading and model merger use the same code | AUTOMATIC | 2022-10-09 | 1 | -3/+3 |
| | | |||||
| * | Merge branch 'master' into fix-vram | Jairo Correa | 2022-09-30 | 1 | -3/+8 |
| |\ | |||||
| | * | fix model checkpoint merger tab failing to save model | AUTOMATIC | 2022-09-30 | 1 | -1/+3 |
| | | | |||||
| | * | remove unwanted formatting/functionality from the PR | AUTOMATIC | 2022-09-30 | 1 | -17/+18 |
| | | | |||||
| | * | Merge remote-tracking branch 'upstream/master' into ModelLoader | d8ahazard | 2022-09-30 | 1 | -23/+31 |
| | |\ | |||||
| | | * | Add custom name and try-except | safentisAuth | 2022-09-29 | 1 | -1/+2 |
| | | | | |||||
| | * | | Holy $hit. | d8ahazard | 2022-09-29 | 1 | -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. | ||||
| | * | | Merge remote-tracking branch 'upstream/master' into ModelLoader | d8ahazard | 2022-09-27 | 1 | -0/+57 |
| | |\ \ | |||||
| | * | | | Re-implement universal model loading | d8ahazard | 2022-09-26 | 1 | -0/+2 |
| | | | | | |||||
| * | | | | Fix memory leak and reduce memory usage | Jairo Correa | 2022-09-29 | 1 | -0/+2 |
| | |_|/ |/| | | |||||
| * | | | update lists of models after merging them in checkpoints tab | AUTOMATIC | 2022-09-28 | 1 | -10/+17 |
| | | | | | | | | | | | | | support saving as half | ||||
| * | | | correctly list and display model names for #1261 | AUTOMATIC | 2022-09-28 | 1 | -15/+8 |
| | | | | |||||
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |