aboutsummaryrefslogtreecommitdiff
path: root/modules
AgeCommit message (Collapse)Author
2022-12-10Merge pull request #4841 from R-N/vae-fix-noneAUTOMATIC1111
Fix None option of VAE selector
2022-12-10add Noise multiplier option to infotextAUTOMATIC
2022-12-10Merge pull request #5373 from mezotaken/masterAUTOMATIC1111
add noise strength parameter similar to NAI
2022-12-10Merge pull request #5404 from szhublox/merger-ram-usageAUTOMATIC1111
Merger ram usage
2022-12-10cleanup some unneeded imports for hijack filesAUTOMATIC
2022-12-10do not replace entire unet for the resolution hackAUTOMATIC
2022-12-10Merge pull request #4978 from aliencaocao/support_any_resolutionAUTOMATIC1111
Patch UNet Forward to support resolutions that are not multiples of 64
2022-12-10Merge pull request #5555 from ywx9/masterAUTOMATIC1111
Bug fix (a few lines in modules/api/api.py)
2022-12-10Merge pull request #5547 from Ju1-js/masterAUTOMATIC1111
Make "# settings changed" grammatically correct
2022-12-09Bug fixywx9
2022-12-08Make # settings changed message grammatically correctJu1-js
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
2022-12-08Add latent upscale option to img2imgAndrew Ryan
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
2022-12-04extras.py: use as little RAM as possible, misc fixesMackerel
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
2022-12-04fix #4459 breaking inpainting when the option is not specified.AUTOMATIC
2022-12-03fix incorrect file extension filter for deepdanbooru modelsAUTOMATIC
2022-12-03use modelloader for #4956AUTOMATIC
2022-12-03Merge pull request #4956 from TiagoSantos81/offline_BLIPAUTOMATIC1111
[CLIP interrogator] use local file, if available
2022-12-03move #5216 to the extensionAUTOMATIC
2022-12-03Merge remote-tracking branch 'wywywywy/autoencoder-hijack'AUTOMATIC
2022-12-03add built-in extension systemAUTOMATIC
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
2022-12-03add comment for #4407 and remove seemingly unnecessary cudnn.enabledAUTOMATIC
2022-12-03fix #4407 breaking UI entirely for card other than ones related to the PRAUTOMATIC
2022-12-03Merge pull request #4407 from yoinked-h/patch-1AUTOMATIC1111
Fix issue with 16xx cards
2022-12-03Merge pull request #5251 from adieyal/bug/negative-prompt-infotextAUTOMATIC1111
Fixed incorrect negative prompt text in infotext
2022-12-03Merge branch 'master' into racecond_fixAUTOMATIC1111
2022-12-03Merge pull request #4459 from kavorite/color-sketch-inpaintingAUTOMATIC1111
add `--gradio-inpaint-tool` and option to specify `color-sketch`
2022-12-03Merge pull request #5194 from brkirch/autocast-and-mps-randn-fixesAUTOMATIC1111
Use devices.autocast() and fix MPS randn issues
2022-12-03more simple config option name plus mouseover hint for clip skipAUTOMATIC
2022-12-03Merge pull request #5304 from space-nuko/fix/clip-skip-applicationAUTOMATIC1111
Fix clip skip of 1 not being restored from prompts
2022-12-03Merge pull request #5328 from jcowens/fix-typoAUTOMATIC1111
fix typo
2022-12-03Merge pull request #5331 from smirkingface/openaimodel_fixAUTOMATIC1111
Fixed AttributeError where openaimodel is not found
2022-12-03Merge pull request #5340 from PhytoEpidemic/masterAUTOMATIC1111
Fix divide by 0 error
2022-12-03prevent include_init_images from being passed to ↵AUTOMATIC
StableDiffusionProcessingImg2Img in API #4989
2022-12-03Merge pull request #5165 from klimaleksus/fix-sequential-vaeAUTOMATIC1111
Make VAE step sequential to prevent VRAM spikes, will fix #3059, #2082, #2561, #3462
2022-12-02Fix divide by 0 errorPhytoEpidemic
Fix of the edge case 0 weight that occasionally will pop up in some specific situations. This was crashing the script.
2022-12-02Fixed AttributeError where openaimodel is not foundSmirkingFace
2022-12-02fix typojcowens
2022-12-02Fixed safe.py for pytorch 1.13 ckpt filesSmirkingFace
2022-12-01Fix clip skip of 1 not being restored from promptsspace-nuko
2022-11-30Rework MPS randn fix, add randn_like fixbrkirch
torch.manual_seed() already sets a CPU generator, so there is no reason to create a CPU generator manually. torch.randn_like also needs a MPS fix for k-diffusion, but a torch hijack with randn_like already exists so it can also be used for that.
2022-11-30Use devices.autocast instead of torch.autocastbrkirch
2022-11-30Add workaround for using MPS with torchsdebrkirch
2022-11-30Fixed incorrect negative prompt text in infotextAdi Eyal
Previously only the first negative prompt in all_negative_prompts was being used for infotext. This fixes that by selecting the index-th negative prompt
2022-11-30Change to steps of 8Billy Cao
2022-11-29Added purpose of this hijack to commentswywywywy
2022-11-29Add autoencoder to sd_hijackwywywywy
generated by cgit v1.2.1 (git 2.18.0) at 2024-09-20 21:29:59 +0000