aboutsummaryrefslogtreecommitdiffstats
path: root/modules
Commit message (Collapse)AuthorAgeFilesLines
* Merge pull request #3874 from cobryan05/extra_tweakAUTOMATIC11112022-10-292-55/+130
|\ | | | | Extras Tab - Option to upscale before face fix, caching improvements
| * extras: upscaler blending should not be considered in cache keyChris OBryan2022-10-281-1/+1
| |
| * extras-tweaks: autoformat changed linesChris OBryan2022-10-281-15/+15
| |
| * extras: Make image cache LRUChris OBryan2022-10-282-29/+43
| | | | | | | | | | | | | | | | | | 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 cacheChris OBryan2022-10-281-20/+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 fixingChris OBryan2022-10-282-50/+99
| | | | | | | | | | | | 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.
* | change default hypernet activation function to linearAUTOMATIC2022-10-291-1/+1
| |
* | Merge pull request #3877 from Yaiol/masterAUTOMATIC11112022-10-291-4/+5
|\ \ | | | | | | Filename tags are wrongly referencing to process size instead of image size
| * | Update images.pyYaiol2022-10-281-4/+5
| |/ | | | | | | Filename tags [height] and [width] are wrongly referencing to process size instead of resulting image size. Making all upscale files named wrongly.
* | Merge pull request #3717 from benkyoujouzu/masterAUTOMATIC11112022-10-291-0/+1
|\ \ | | | | | | Add missing support for linear activation in hypernetwork
| * | Add missing support for linear activation in hypernetworkbenkyoujouzu2022-10-281-0/+1
| |/
* | Merge pull request #3771 from aria1th/patch-12AUTOMATIC11112022-10-291-1/+2
|\ \ | | | | | | Disable unavailable or duplicate options for Activation functions
| * | Re enable linearAngelBottomless2022-10-281-1/+1
| | |
| * | Disable unavailable or duplicate optionsAngelBottomless2022-10-271-1/+2
| |/
* | Merge branch 'AUTOMATIC1111:master' into masterBruno Seoane2022-10-291-1/+1
|\|
| * typo: cmd_opts.embedding_dir to cmd_opts.embeddings_dirDepFA2022-10-261-1/+1
| |
* | Remove folder endpointBruno Seoane2022-10-262-14/+1
| |
* | Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webuiBruno Seoane2022-10-2618-87/+637
|\|
| * add script callback for before image save and change callback for after ↵AUTOMATIC2022-10-262-26/+64
| | | | | | | | image save to use a class with parameters
| * add override_settings to API as an alternative to #3629AUTOMATIC2022-10-262-7/+22
| |
| * Implement PR #3625 but for embeddings.timntorres2022-10-261-1/+1
| |
| * Implement PR #3309 but for embeddings.timntorres2022-10-261-1/+8
| |
| * Implement PR #3189 but for embeddings.timntorres2022-10-261-5/+5
| |
| * patch bug (SeverianVoid's comment on 5245c7a)timntorres2022-10-261-1/+1
| |
| * img2img, use smartphone photos' EXIF orientationtimntorres2022-10-261-0/+8
| |
| * fix typo in on_save_imaged/on_image_saved; hope no extension is using it yetAUTOMATIC2022-10-261-1/+1
| |
| * default_time_format if format is blankw-e-w2022-10-261-1/+1
| |
| * images: allow nested bracket in filename patternMilly2022-10-261-7/+4
| |
| * cleanStephen2022-10-262-5/+1
| |
| * [Bugfix][API] - Fix API response for colab usersStephen2022-10-262-8/+19
| |
| * enable creating embedding with --medvramAUTOMATIC2022-10-261-0/+3
| |
| * Merge pull request #3139 from captin411/focal-point-croppingAUTOMATIC11112022-10-263-5/+392
| |\ | | | | | | [Preprocess image] New option to auto crop based on complexity, edges, faces
| | * update default weightscaptin4112022-10-262-9/+9
| | |
| | * download better face detection module dynamicallycaptin4112022-10-252-2/+31
| | |
| | * Focal crop UI elementscaptin4112022-10-252-15/+31
| | |
| | * Merge branch 'master' into focal-point-croppingcaptin4112022-10-2534-884/+2120
| | |\
| | * | improve debug markers, fix algo weightingcaptin4112022-10-251-78/+129
| | | |
| | * | auto cropping now works with non square cropscaptin4112022-10-231-240/+269
| | | |
| | * | improve face detection a lotcaptin4112022-10-201-37/+62
| | | |
| | * | face detection algo, configurability, reusabilitycaptin4112022-10-202-136/+230
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Try to move the crop in the direction of a face if it is present More internal configuration options for choosing weights of each of the algorithm's findings Move logic into its module
| | * | fix entropy point calculationcaptin4112022-10-191-15/+19
| | | |
| | * | UI changes for focal point image croppingcaptin4112022-10-191-1/+3
| | | |
| | * | Add auto focal point cropping to Preprocess imagescaptin4112022-10-191-5/+146
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This algorithm plots a bunch of points of interest on the source image and averages their locations to find a center. Most points come from OpenCV. One point comes from an entropy model. OpenCV points account for 50% of the weight and the entropy based point is the other 50%. The center of all weighted points is calculated and a bounding box is drawn as close to centered over that point as possible.
| * | | remove duplicate keys and lowercaseAngelBottomless2022-10-261-1/+1
| | | |
| * | | Weight initialization and More activation funcAngelBottomless2022-10-263-11/+44
| | |/ | |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | add weight init add weight init option in create_hypernetwork fstringify hypernet info save weight initialization info for further debugging fill bias with zero for He/Xavier initialize LayerNorm with Normal fix loading weight_init
| * | update callbacks code for #3549AUTOMATIC2022-10-251-6/+16
| | |
| * | fix default filename patternw-e-w2022-10-251-1/+3
| | |
| * | MPS Upscalers Fixbrkirch2022-10-254-4/+7
| | | | | | | | | | | | Get ESRGAN, SCUNet, and SwinIR working correctly on MPS by ensuring memory is contiguous for tensor views before sending to MPS device.
| * | Remove BSRGAN from --use-cpu, add SwinIRbrkirch2022-10-253-10/+10
| | |
| * | Merge branch 'master' into on-image-saved-callbackAUTOMATIC11112022-10-259-542/+207
| |\ \
generated by cgit v1.2.3 (git 2.25.1) at 2025-05-10 00:27:52 +0000