| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2022-10-29 | Merge pull request #3874 from cobryan05/extra_tweak | AUTOMATIC1111 | -55/+130 | |
| Extras Tab - Option to upscale before face fix, caching improvements | ||||
| 2022-10-29 | change default hypernet activation function to linear | AUTOMATIC | -1/+1 | |
| 2022-10-29 | Merge pull request #3877 from Yaiol/master | AUTOMATIC1111 | -4/+5 | |
| Filename tags are wrongly referencing to process size instead of image size | ||||
| 2022-10-29 | Merge pull request #3717 from benkyoujouzu/master | AUTOMATIC1111 | -0/+1 | |
| Add missing support for linear activation in hypernetwork | ||||
| 2022-10-29 | Merge pull request #3771 from aria1th/patch-12 | AUTOMATIC1111 | -1/+2 | |
| Disable unavailable or duplicate options for Activation functions | ||||
| 2022-10-28 | Merge branch 'AUTOMATIC1111:master' into master | Bruno Seoane | -1/+1 | |
| 2022-10-29 | Re enable linear | AngelBottomless | -1/+1 | |
| 2022-10-29 | Update images.py | Yaiol | -4/+5 | |
| Filename tags [height] and [width] are wrongly referencing to process size instead of resulting image size. Making all upscale files named wrongly. | ||||
| 2022-10-28 | extras: upscaler blending should not be considered in cache key | Chris OBryan | -1/+1 | |
| 2022-10-28 | extras-tweaks: autoformat changed lines | Chris OBryan | -15/+15 | |
| 2022-10-28 | extras: Make image cache LRU | Chris OBryan | -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. | ||||
| 2022-10-28 | extras: Rework image cache | Chris 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. | ||||
| 2022-10-28 | extras: Add option to run upscaling before face fixing | Chris OBryan | -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. | ||||
| 2022-10-28 | Add missing support for linear activation in hypernetwork | benkyoujouzu | -0/+1 | |
| 2022-10-27 | Disable unavailable or duplicate options | AngelBottomless | -1/+2 | |
| 2022-10-26 | typo: cmd_opts.embedding_dir to cmd_opts.embeddings_dir | DepFA | -1/+1 | |
| 2022-10-26 | Remove folder endpoint | Bruno Seoane | -14/+1 | |
| 2022-10-26 | Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webui | Bruno Seoane | -87/+637 | |
| 2022-10-26 | add script callback for before image save and change callback for after ↵ | AUTOMATIC | -26/+64 | |
| image save to use a class with parameters | ||||
| 2022-10-26 | add override_settings to API as an alternative to #3629 | AUTOMATIC | -7/+22 | |
| 2022-10-26 | Implement PR #3625 but for embeddings. | timntorres | -1/+1 | |
| 2022-10-26 | Implement PR #3309 but for embeddings. | timntorres | -1/+8 | |
| 2022-10-26 | Implement PR #3189 but for embeddings. | timntorres | -5/+5 | |
| 2022-10-26 | patch bug (SeverianVoid's comment on 5245c7a) | timntorres | -1/+1 | |
| 2022-10-26 | img2img, use smartphone photos' EXIF orientation | timntorres | -0/+8 | |
| 2022-10-26 | fix typo in on_save_imaged/on_image_saved; hope no extension is using it yet | AUTOMATIC | -1/+1 | |
| 2022-10-26 | default_time_format if format is blank | w-e-w | -1/+1 | |
| 2022-10-26 | images: allow nested bracket in filename pattern | Milly | -7/+4 | |
| 2022-10-26 | clean | Stephen | -5/+1 | |
| 2022-10-26 | [Bugfix][API] - Fix API response for colab users | Stephen | -8/+19 | |
| 2022-10-26 | enable creating embedding with --medvram | AUTOMATIC | -0/+3 | |
| 2022-10-26 | Merge pull request #3139 from captin411/focal-point-cropping | AUTOMATIC1111 | -5/+392 | |
| [Preprocess image] New option to auto crop based on complexity, edges, faces | ||||
| 2022-10-26 | remove duplicate keys and lowercase | AngelBottomless | -1/+1 | |
| 2022-10-26 | Weight initialization and More activation func | AngelBottomless | -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 | ||||
| 2022-10-25 | update default weights | captin411 | -9/+9 | |
| 2022-10-25 | download better face detection module dynamically | captin411 | -2/+31 | |
| 2022-10-25 | Focal crop UI elements | captin411 | -15/+31 | |
| 2022-10-25 | Merge branch 'master' into focal-point-cropping | captin411 | -884/+2120 | |
| 2022-10-25 | improve debug markers, fix algo weighting | captin411 | -78/+129 | |
| 2022-10-25 | update callbacks code for #3549 | AUTOMATIC | -6/+16 | |
| 2022-10-25 | fix default filename pattern | w-e-w | -1/+3 | |
| 2022-10-25 | MPS Upscalers Fix | brkirch | -4/+7 | |
| Get ESRGAN, SCUNet, and SwinIR working correctly on MPS by ensuring memory is contiguous for tensor views before sending to MPS device. | ||||
| 2022-10-25 | Remove BSRGAN from --use-cpu, add SwinIR | brkirch | -10/+10 | |
| 2022-10-25 | Merge branch 'master' into on-image-saved-callback | AUTOMATIC1111 | -542/+207 | |
| 2022-10-25 | do not stop execution when script's callback misbehaves and report which ↵ | AUTOMATIC | -9/+36 | |
| script it was | ||||
| 2022-10-25 | fix #3145 #3093 | ritosonn | -2/+2 | |
| 2022-10-24 | UnknownTimeZoneError | w-e-w | -1/+4 | |
| 2022-10-24 | Merge remote-tracking branch 'upstream/master' | Bruno Seoane | -548/+194 | |
| 2022-10-24 | Reverse run_extras change | Bruno Seoane | -6/+11 | |
| Update serialization on the batch images endpoint | ||||
| 2022-10-24 | rename api/processing to api/models for #3511 | AUTOMATIC | -1/+1 | |
 |
index : stable-diffusion-webui-gfx803.git | |
| stable-diffusion-webui by AUTOMATIC1111 with patches for gfx803 GPU and Dockerfile |
| aboutsummaryrefslogtreecommitdiffstats |