aboutsummaryrefslogtreecommitdiffstats
path: root/modules
Commit message (Collapse)AuthorAgeFilesLines
* 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
* make it possible to merge inpainting model with non-inpainting oneAUTOMATIC2022-12-041-2/+25
|
* fix #4459 breaking inpainting when the option is not specified.AUTOMATIC2022-12-032-19/+23
|
* fix incorrect file extension filter for deepdanbooru modelsAUTOMATIC2022-12-031-1/+1
|
* use modelloader for #4956AUTOMATIC2022-12-031-14/+8
|
* Merge pull request #4956 from TiagoSantos81/offline_BLIPAUTOMATIC11112022-12-031-1/+12
|\ | | | | [CLIP interrogator] use local file, if available
| * [interrogator] mkdir checkTiago F. Santos2022-11-241-6/+10
| |
| * [CLIP interrogator] use local file, if availableTiago F. Santos2022-11-221-1/+8
| |
* | move #5216 to the extensionAUTOMATIC2022-12-032-287/+1
| |
* | Merge remote-tracking branch 'wywywywy/autoencoder-hijack'AUTOMATIC2022-12-032-1/+287
|\ \
| * | Added purpose of this hijack to commentswywywywy2022-11-291-0/+4
| | |
| * | Add autoencoder to sd_hijackwywywywy2022-11-291-1/+1
| | |
| * | Hijack VQModelInterface back to AutoEncoderwywywywy2022-11-291-0/+282
| | |
* | | add built-in extension systemAUTOMATIC2022-12-0313-2710/+42
| | | | | | | | | | | | | | | add support for adding upscalers in extensions move LDSR, ScuNET and SwinIR to built-in extensions
* | | add comment for #4407 and remove seemingly unnecessary cudnn.enabledAUTOMATIC2022-12-031-1/+3
| | |
* | | fix #4407 breaking UI entirely for card other than ones related to the PRAUTOMATIC2022-12-031-4/+2
| | |
* | | Merge pull request #4407 from yoinked-h/patch-1AUTOMATIC11112022-12-031-0/+7
|\ \ \ | | | | | | | | Fix issue with 16xx cards
| * | | actual better fixpepe10-gpu2022-11-081-5/+2
| | | | | | | | | | | | thanks C43H66N12O12S2
| * | | terrible hackpepe10-gpu2022-11-081-2/+9
| | | |
| * | | 16xx card fixpepe10-gpu2022-11-071-0/+3
| | | | | | | | | | | | cudnn
* | | | Merge pull request #5251 from adieyal/bug/negative-prompt-infotextAUTOMATIC11112022-12-031-1/+1
|\ \ \ \ | | | | | | | | | | Fixed incorrect negative prompt text in infotext
| * | | | Fixed incorrect negative prompt text in infotextAdi Eyal2022-11-301-1/+1
| | |/ / | |/| | | | | | | | | | | | | | | | | | 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
* | | | Merge branch 'master' into racecond_fixAUTOMATIC11112022-12-0350-1375/+3161
|\ \ \ \
| * \ \ \ Merge pull request #4459 from kavorite/color-sketch-inpaintingAUTOMATIC11112022-12-033-10/+36
| |\ \ \ \ | | | | | | | | | | | | add `--gradio-inpaint-tool` and option to specify `color-sketch`
| | * | | | blur mask with color-sketch + add paint transparency sliderkavorite2022-11-092-8/+16
| | | | | |
| | * | | | add new color-sketch state to img2img invocationkavorite2022-11-081-0/+1
| | | | | |
| | * | | | add gradio-inpaint-tool; color-sketchkavorite2022-11-083-7/+24
| | | | | |
| * | | | | Merge pull request #5194 from brkirch/autocast-and-mps-randn-fixesAUTOMATIC11112022-12-038-31/+29
| |\ \ \ \ \ | | | | | | | | | | | | | | Use devices.autocast() and fix MPS randn issues
| | * | | | | Rework MPS randn fix, add randn_like fixbrkirch2022-11-302-15/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | 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.
| | * | | | | Use devices.autocast instead of torch.autocastbrkirch2022-11-305-11/+6
| | | | | | |
| | * | | | | Add workaround for using MPS with torchsdebrkirch2022-11-301-0/+14
| | | | | | |
| | * | | | | Refactor and instead check if mps is being used, not availabilitybrkirch2022-11-291-5/+1
| | | | | | |
| * | | | | | more simple config option name plus mouseover hint for clip skipAUTOMATIC2022-12-031-1/+1
| | | | | | |
| * | | | | | Merge pull request #5304 from space-nuko/fix/clip-skip-applicationAUTOMATIC11112022-12-032-1/+5
| |\ \ \ \ \ \ | | | | | | | | | | | | | | | | Fix clip skip of 1 not being restored from prompts
| | * | | | | | Fix clip skip of 1 not being restored from promptsspace-nuko2022-12-012-1/+5
| | | |_|/ / / | | |/| | | |
| * | | | | | Merge pull request #5328 from jcowens/fix-typoAUTOMATIC11112022-12-031-1/+1
| |\ \ \ \ \ \ | | | | | | | | | | | | | | | | fix typo
| | * | | | | | fix typojcowens2022-12-021-1/+1
| | |/ / / / /
| * | | | | | Merge pull request #5331 from smirkingface/openaimodel_fixAUTOMATIC11112022-12-031-0/+1
| |\ \ \ \ \ \ | | | | | | | | | | | | | | | | Fixed AttributeError where openaimodel is not found
| | * | | | | | Fixed AttributeError where openaimodel is not foundSmirkingFace2022-12-021-0/+1
| | |/ / / / /
| * | | | | | Merge pull request #5340 from PhytoEpidemic/masterAUTOMATIC11112022-12-031-3/+3
| |\ \ \ \ \ \ | | | | | | | | | | | | | | | | Fix divide by 0 error
| | * | | | | | Fix divide by 0 errorPhytoEpidemic2022-12-021-3/+3
| | |/ / / / / | | | | | | | | | | | | | | Fix of the edge case 0 weight that occasionally will pop up in some specific situations. This was crashing the script.
| * | | | | | prevent include_init_images from being passed to ↵AUTOMATIC2022-12-031-2/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | StableDiffusionProcessingImg2Img in API #4989
| * | | | | | Merge pull request #5165 from klimaleksus/fix-sequential-vaeAUTOMATIC11112022-12-031-2/+2
| |\ \ \ \ \ \ | | | | | | | | | | | | | | | | Make VAE step sequential to prevent VRAM spikes, will fix #3059, #2082, #2561, #3462
| | * | | | | | Make VAE step sequential to prevent VRAM spikesklimaleksus2022-11-281-2/+2
| | | |/ / / / | | |/| | | |
| * | | | | | Fixed safe.py for pytorch 1.13 ckpt filesSmirkingFace2022-12-021-7/+11
| | |/ / / / | |/| | | |
| * | | | | Merge remote-tracking branch 'pattontim/safetensors'AUTOMATIC2022-11-291-0/+1
| |\ \ \ \ \ | | |/ / / / | |/| | | |
| | * | | | safetensors optional for nowTim Patton2022-11-221-1/+8
| | | | | |
| | * | | | Use GPU for loading safetensors, disable exportTim Patton2022-11-212-3/+5
| | | | | |
| | * | | | Patch line ui endingsTim Patton2022-11-211-1814/+1814
| | | | | |
| | * | | | Generalize SD torch load/save to implement safetensor merging compatTim Patton2022-11-203-1826/+1840
| | | | | |
generated by cgit v1.2.3 (git 2.25.1) at 2025-05-02 12:48:04 +0000