aboutsummaryrefslogtreecommitdiffstats
path: root/modules
Commit message (Collapse)AuthorAgeFilesLines
...
| | * | fix bugzhaohu xing2022-12-021-1/+5
| | | | | | | | | | | | | | | | Signed-off-by: zhaohu xing <920232796@qq.com>
| * | | Merge branch 'AUTOMATIC1111:master' into masterZac Liu2022-12-0627-2775/+190
| |\ \ \ | | |/ / | |/| |
| * | | fix bugszhaohu xing2022-11-303-9/+153
| | | | | | | | | | | | | | | | Signed-off-by: zhaohu xing <920232796@qq.com>
| * | | Merge branch 'master' into masterzhaohu xing2022-11-3031-820/+1269
| |\ \ \
| * | | | add AltDiffusion to webuizhaohu xing2022-11-293-9/+24
| | | | | | | | | | | | | | | | | | | | Signed-off-by: zhaohu xing <920232796@qq.com>
* | | | | set sd_model for API later, inside the lock, to prevent multiple requests ↵AUTOMATIC2022-12-311-6/+5
| | | | | | | | | | | | | | | | | | | | with different models ending up with incorrect results #5877 #6012
* | | | | Merge pull request #6015 from philpax/api-begin-end-in-queueAUTOMATIC11112022-12-311-8/+4
|\ \ \ \ \ | | | | | | | | | | | | fix(api): only begin/end state in lock
| * | | | | fix(api): only begin/end state in lockPhilpax2022-12-251-8/+4
| | | | | |
* | | | | | Merge pull request #6017 from hitomi/masterAUTOMATIC11112022-12-312-6/+26
|\ \ \ \ \ \ | | | | | | | | | | | | | | Add memory cache for VAE weights
| * | | | | | Add memory cache for VAE weightshitomi2022-12-252-6/+26
| |/ / / / /
* | | | | | Merge pull request #6037 from vladmandic/masterAUTOMATIC11112022-12-311-0/+3
|\ \ \ \ \ \ | | | | | | | | | | | | | | fix rgba to rgb when using jpeg output
| * | | | | | fix rgba to rgb when using jpeg outputVladimir Mandic2022-12-261-0/+3
| | |_|_|_|/ | |/| | | |
* | | | | | Merge pull request #6133 from vladmandic/memmon-statsAUTOMATIC11112022-12-311-0/+3
|\ \ \ \ \ \ | | | | | | | | | | | | | | add additional memory states
| * | | | | | add additional memory statesVladimir Mandic2022-12-311-0/+3
| |/ / / / /
* | | | | | Merge pull request #6134 from vladmandic/remove-console-messageAUTOMATIC11112022-12-311-1/+1
|\ \ \ \ \ \ | | | | | | | | | | | | | | remove unnecessary console message
| * | | | | | remove unnecessary console messageVladimir Mandic2022-12-311-1/+1
| |/ / / / /
* / / / / / fix shared state dictionaryVladimir Mandic2022-12-311-1/+1
|/ / / / /
* / / / / make it so that blank ENSD does not break image generationAUTOMATIC2022-12-261-3/+4
|/ / / /
* | | | Merge pull request #6003 from eaglgenes101/settings-css-classesAUTOMATIC11112022-12-251-2/+2
|\ \ \ \ | | | | | | | | | | Add CSS classes for the settings panels
| * | | | Add CSS classes for the settings panelseaglgenes1012022-12-251-2/+2
| | | | |
* | | | | Merge pull request #5992 from yuvalabou/F541AUTOMATIC11112022-12-258-16/+16
|\ \ \ \ \ | | | | | | | | | | | | Fix F541: f-string without any placeholders
| * | | | | fix F541 f-string without any placeholdersYuval Aboulafia2022-12-248-16/+16
| | | | | |
* | | | | | Merge pull request #6005 from allenbenz/patch-1AUTOMATIC11112022-12-251-1/+1
|\ \ \ \ \ \ | | | | | | | | | | | | | | Fix clip interrogate from the webui
| * | | | | | Fix clip interrogate from the webuiAllen Benz2022-12-251-1/+1
| | |/ / / / | |/| | | | | | | | | | | | | | | | A recent change made the image RGBA, which makes the clip interrogator unhappy. deepbooru and calling the interrogator from the api already do the conversion so this is the only place that needed it.
* | | | | | Merge pull request #5999 from vladmandic/trainapiAUTOMATIC11112022-12-254-28/+132
|\ \ \ \ \ \ | | | | | | | | | | | | | | implement train api
| * | | | | | implement train apiVladimir Mandic2022-12-244-28/+132
| |/ / / / /
* / / / / / a way to add an exception to unpickler without explicitly calling ↵AUTOMATIC2022-12-251-1/+38
|/ / / / / | | | | | | | | | | | | | | | load_with_extra
* | | | | change wording a bitAUTOMATIC2022-12-241-1/+1
| | | | |
* | | | | added cheap NN approximation for VAEAUTOMATIC2022-12-243-16/+77
|/ / / /
* | | | Merge pull request #5977 from philpax/api-dont-save-extras-outputAUTOMATIC11112022-12-242-11/+12
|\ \ \ \ | | | | | | | | | | fix(api): don't save extras output to disk
| * | | | fix(api): don't save extras output to diskPhilpax2022-12-242-11/+12
| | | | |
* | | | | Merge pull request #5976 from AbstractQbit/fast_previewAUTOMATIC11112022-12-242-9/+19
|\ \ \ \ \ | | | | | | | | | | | | Add an option for faster low quality previews
| * | | | | Add an option for faster low quality previewsAbstractQbit2022-12-242-9/+19
| |/ / / /
* | | | | separate part of denoiser code into a function to make it easier for ↵AUTOMATIC2022-12-241-6/+11
| | | | | | | | | | | | | | | | | | | | extensions to override it
* | | | | added an option to filter out deepbooru tagsAUTOMATIC2022-12-242-1/+4
| | | | |
* | | | | Removed lenght in sd_model at line 115linuxmobile ( リナックス )2022-12-241-3/+0
|/ / / / | | | | | | | | | | | | | | | | Commit eba60a4 is what is causing this error, delete the length check in sd_model starting at line 115 and it's fine. https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/5971#issuecomment-1364507379
* | | | Merge pull request #5627 from deanpress/patch-1AUTOMATIC11112022-12-241-0/+4
|\ \ \ \ | | | | | | | | | | fix: fallback model_checkpoint if it's empty
| * | | | fix: fallback model_checkpoint if it's emptyDean van Dugteren2022-12-111-0/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This fixes the following error when SD attempts to start with a deleted checkpoint: ``` Traceback (most recent call last): File "D:\Web\stable-diffusion-webui\launch.py", line 295, in <module> start() File "D:\Web\stable-diffusion-webui\launch.py", line 290, in start webui.webui() File "D:\Web\stable-diffusion-webui\webui.py", line 132, in webui initialize() File "D:\Web\stable-diffusion-webui\webui.py", line 62, in initialize modules.sd_models.load_model() File "D:\Web\stable-diffusion-webui\modules\sd_models.py", line 283, in load_model checkpoint_info = checkpoint_info or select_checkpoint() File "D:\Web\stable-diffusion-webui\modules\sd_models.py", line 117, in select_checkpoint checkpoint_info = checkpoints_list.get(model_checkpoint, None) TypeError: unhashable type: 'list' ```
* | | | | Merge pull request #5637 from aednzxy/patch-1AUTOMATIC11112022-12-241-0/+4
|\ \ \ \ \ | | | | | | | | | | | | API endpoint to refresh checkpoints
| * | | | | API endpoint to refresh checkpointsDean Hopkins2022-12-111-0/+4
| |/ / / / | | | | | | | | | | API endpoint to refresh checkpoints
* | | | | Merge pull request #5131 from uservar/inpainting-detectionAUTOMATIC11112022-12-241-1/+4
|\ \ \ \ \ | | | | | | | | | | | | Better should_hijack_inpainting detection
| * | | | | Better should hijack inpainting detectionuservar2022-11-271-1/+4
| | | | | |
* | | | | | Merge pull request #5718 from space-nuko/feature/save-hypernetwork-hashAUTOMATIC11112022-12-242-2/+36
|\ \ \ \ \ \ | | | | | | | | | | | | | | Save hypernetwork hash and fix hypernetwork parameter restoring
| * | | | | | Fix commentspace-nuko2022-12-131-1/+1
| | | | | | |
| * | | | | | Correctly restore default hypernetwork strengthspace-nuko2022-12-131-0/+3
| | | | | | |
| * | | | | | Correctly restore hypernetwork from hashspace-nuko2022-12-131-0/+30
| | | | | | |
| * | | | | | Save hypernetwork hash in infotextspace-nuko2022-12-131-2/+3
| | |/ / / / | |/| | | |
* | | | | | rename the option for img2img latent upscaleAUTOMATIC2022-12-242-2/+2
| | | | | |
* | | | | | Merge pull request #5521 from AndrewRyanChama/ryan/img2imglatentscaleAUTOMATIC11112022-12-242-2/+6
|\ \ \ \ \ \ | | | | | | | | | | | | | | Add latent upscale option to img2img
| * | | | | | Add latent upscale option to img2imgAndrew Ryan2022-12-082-2/+6
| | |_|_|_|/ | |/| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Recently, the option to do latent upscale was added to txt2img highres fix. This feature runs by scaling the latent sample of the image, and then running a second pass of img2img. But, in this edition of highres fix, the image and parameters cannot be changed between the first pass and second pass. We might want to do a fixup in img2img before doing the second pass, or might want to run the second pass at a different resolution. This change adds the option for img2img to perform its upscale in latent space, rather than image space, giving very similar results to highres fix with latent upscale. The result is not exactly the same because there is an additional latent -> decoder -> image -> encoder -> latent that won't happen in highres fix, but this conversion has relatively small losses
generated by cgit v1.2.3 (git 2.25.1) at 2025-05-09 08:08:19 +0000