aboutsummaryrefslogtreecommitdiffstats
path: root/modules
AgeCommit message (Collapse)AuthorLines
2022-12-17Add numpy fix for MPS on PyTorch 1.12.1brkirch-0/+9
When saving training results with torch.save(), an exception is thrown: "RuntimeError: Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead." So for MPS, check if Tensor.requires_grad and detach() if necessary.
2022-12-17fix: Modify font size when unable to fit in plotMMaker-7/+16
This prevents scenarios where text without line breaks will start overlapping with each other when generating X/Y plots. This is most evident when generating X/Y plots with checkpoints, as most don't contain spaces and sometimes include extra information such as the epoch, making it extra long.
2022-12-16apply to DPM2 (non-ancestral) as wellAlex "mcmonkey" Goodwin-1/+1
2022-12-16Add a workaround patch for DPM2 a issueAlex "mcmonkey" Goodwin-0/+3
DPM2 a and DPM2 a Karras samplers are both affected by an issue described by https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/3483 and can be resolved by a workaround suggested by the k-diffusion author at https://github.com/crowsonkb/k-diffusion/issues/43#issuecomment-1305195666
2022-12-16fix: xformersAkiba-0/+18
2022-12-14Fix various typosJim Hays-40/+40
2022-12-14Correct singleton comparisonsYuval Aboulafia-5/+9
2022-12-13Fix commentspace-nuko-1/+1
2022-12-13Correctly restore default hypernetwork strengthspace-nuko-0/+3
2022-12-13Correctly restore hypernetwork from hashspace-nuko-0/+30
2022-12-13Save hypernetwork hash in infotextspace-nuko-2/+3
2022-12-11Improve color correction with luminosity blendThereforeGames-3/+6
2022-12-11API endpoint to refresh checkpointsDean Hopkins-0/+4
API endpoint to refresh checkpoints
2022-12-11unconditionally set use_ema=False if value not specified (True never worked, ↵MrCheeze-1/+3
and all configs except v1-inpainting-inference.yaml already correctly set it to False)
2022-12-11fix: fallback model_checkpoint if it's emptyDean van Dugteren-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' ```
2022-12-10fix support for 2.0 inpainting model while maintaining support for 1.5 ↵MrCheeze-2/+2
inpainting model
2022-12-10unload depth model if medvram/lowvram enabledMrCheeze-5/+7
2022-12-10Merge pull request #5191 from ↵AUTOMATIC1111-2/+8
aliencaocao/enable_checkpoint_switching_in_override_settings Support changing checkpoint and vae through override_settings
2022-12-10add an 'installed' tag to extensionsAUTOMATIC-4/+9
2022-12-10remove NSFW filter and its dependency; if you still want it, find it in the ↵AUTOMATIC-47/+23
extensions section
2022-12-10use less javascript for this non-js-only implementation of the clear prompt ↵AUTOMATIC-13/+11
button.
2022-12-10Merge pull request #3198 from papuSpartan/masterAUTOMATIC1111-3/+29
Add Clear Prompt button to roll_col
2022-12-10Merge pull request #5119 from 0xb8/masterAUTOMATIC1111-22/+29
Atomically rename saved image to avoid race condition with other processes
2022-12-10Merge pull request #5441 from timntorres/add-5433-avoid-sending-size-optionAUTOMATIC1111-2/+2
Add option to avoid sending size between interfaces.
2022-12-10Merge branch 'AUTOMATIC1111:master' into masterpapuSpartan-4085/+2971
2022-12-10Merge pull request #4841 from R-N/vae-fix-noneAUTOMATIC1111-20/+19
Fix None option of VAE selector
2022-12-10add Noise multiplier option to infotextAUTOMATIC-3/+8
2022-12-10Merge pull request #5373 from mezotaken/masterAUTOMATIC1111-0/+2
add noise strength parameter similar to NAI
2022-12-10Merge pull request #5404 from szhublox/merger-ram-usageAUTOMATIC1111-18/+19
Merger ram usage
2022-12-10cleanup some unneeded imports for hijack filesAUTOMATIC-11/+2
2022-12-10do not replace entire unet for the resolution hackAUTOMATIC-30/+33
2022-12-10Merge pull request #4978 from aliencaocao/support_any_resolutionAUTOMATIC1111-12/+44
Patch UNet Forward to support resolutions that are not multiples of 64
2022-12-10Merge pull request #5555 from ywx9/masterAUTOMATIC1111-6/+1
Bug fix (a few lines in modules/api/api.py)
2022-12-10Merge pull request #5547 from Ju1-js/masterAUTOMATIC1111-1/+1
Make "# settings changed" grammatically correct
2022-12-09Bug fixywx9-6/+1
2022-12-08Make # settings changed message grammatically correctJu1-js-1/+1
Make the ": " in the settings changed message not show if 0 settings were changed. "0 settings changed: ." -> "0 settings changed."
2022-12-08Depth2img model supportJay Smith-4/+80
2022-12-08Add latent upscale option to img2imgAndrew Ryan-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
2022-12-05Add opt. to avoid sending size between interfaces.timntorres-2/+2
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
2022-12-04fix #4459 breaking inpainting when the option is not specified.AUTOMATIC-19/+23
2022-12-03fix incorrect file extension filter for deepdanbooru modelsAUTOMATIC-1/+1
2022-12-03use modelloader for #4956AUTOMATIC-14/+8
2022-12-03Merge pull request #4956 from TiagoSantos81/offline_BLIPAUTOMATIC1111-1/+12
[CLIP interrogator] use local file, if available
2022-12-03move #5216 to the extensionAUTOMATIC-287/+1
2022-12-03Merge remote-tracking branch 'wywywywy/autoencoder-hijack'AUTOMATIC-1/+287
2022-12-03add built-in extension systemAUTOMATIC-2710/+42
add support for adding upscalers in extensions move LDSR, ScuNET and SwinIR to built-in extensions
2022-12-03add noise strength parameter similar to NAIVladimir Repin-0/+2
2022-12-03add comment for #4407 and remove seemingly unnecessary cudnn.enabledAUTOMATIC-1/+3
generated by cgit v1.2.3 (git 2.39.1) at 2025-10-17 21:05:54 +0000