aboutsummaryrefslogtreecommitdiffstats
path: root/modules/processing.py
AgeCommit message (Collapse)AuthorLines
2023-08-13use dataclass for StableDiffusionProcessingAUTOMATIC1111-146/+172
2023-08-13add refiner to StableDiffusionProcessing classAUTOMATIC1111-8/+30
write out correct model name in infotext, rather than the refiner model
2023-08-12make it possible to use hires fix together with refinerAUTOMATIC1111-0/+6
2023-08-12put refiner into main UI, into the new accordions sectionAUTOMATIC1111-7/+15
add VAE from main model into infotext, not from refiner model option to make scripts UI without gr.Group fix inconsistencies with refiner when usings samplers that do more denoising than steps
2023-08-11Fix color correction by converting image to RGBcatboxanon-1/+1
2023-08-11Merge pull request #12470 from Splendide-Imaginarius/mask-blur-property+kernelAUTOMATIC1111-5/+20
Make `StableDiffusionProcessingImg2Img.mask_blur` a property, make more inline with PIL `GaussianBlur`
2023-08-10Merge branch 'shared-hires-prompt-raw' into shared-hires-prompt-testRobert Barron-8/+12
2023-08-10Merge branch 'dev' into refinerAUTOMATIC1111-123/+80
2023-08-10add VAE to infotextAUTOMATIC1111-0/+2
2023-08-10fix --use-textbox-seedAUTOMATIC1111-2/+10
2023-08-10face restoration and tiling moved to settings - use "Options in main UI" ↵AUTOMATIC1111-2/+9
setting if you want them back
2023-08-10add a custom UI element that combines accordion and checkboxAUTOMATIC1111-37/+40
rework hires fix UI to use accordion prevent bogus progress output in console when calculating hires fix dimensions
2023-08-09Add slerp import for extension backwards compatcatboxanon-0/+1
2023-08-09allow first pass and hires pass to use a single prompt to do different ↵Robert Barron-8/+12
prompt editing, hires is 1.0..2.0: relative time range is [1..2] absolute time range is [steps+1..steps+hire_steps], e.g. with 30 steps and 20 hires steps, '20' is 2/3rds through first pass, and 40 is halfway through hires pass
2023-08-09rework RNG to use generators instead of generating noises beforehandAUTOMATIC1111-79/+10
2023-08-09fix styles missing from the prompt in infotext when making a grid of batch ↵AUTOMATIC1111-2/+7
of multiplie images
2023-08-08Merge pull request #12412 from dhwz/devAUTOMATIC1111-1/+1
fix typo
2023-08-08fix webui not switching back to original model from refiner when batch count ↵AUTOMATIC1111-0/+2
is greater than 1
2023-08-08Merge branch 'dev' into refinerAUTOMATIC1111-3/+0
2023-08-08REMOVEAUTOMATIC1111-3/+0
2023-08-08fix typodhwz-1/+1
2023-08-06add infotextAUTOMATIC1111-0/+10
add proper support for recalculating conds in k-diffusion samplers remove support for compvis samplers
2023-08-06initial refiner supportAUTOMATIC1111-0/+4
2023-08-06enable cond cache by defaultAUTOMATIC1111-13/+18
2023-08-06fix rework saving incomplete imagesAUTOMATIC1111-1/+1
2023-08-06do the same for s_tmax #12345AUTOMATIC1111-2/+2
2023-08-06Merge branch 'dev' into fix/s-noiseAUTOMATIC1111-9/+12
2023-08-06rework saving incomplete imagesAUTOMATIC1111-9/+9
2023-08-06Merge pull request #12338 from AUTOMATIC1111/dont-save-incomplete-imagesAUTOMATIC1111-8/+11
don't save incomplete images
2023-08-05Correct s_noise fixcatboxanon-2/+2
2023-08-05Attempt to read s_tmax from arg first if option not foundcatboxanon-1/+1
2023-08-05Add s_tmaxcatboxanon-1/+1
2023-08-05Allow s_noise override to actually be usedcatboxanon-1/+1
2023-08-05Option to not save incomplete imagesw-e-w-8/+11
2023-08-05do not add VAE Encoder/Decoder to infotext if it's the defaultAUTOMATIC1111-3/+9
2023-08-05Fix some merge mistakesKohaku-Blueleaf-1/+2
2023-08-05Merge branch 'dev' into efficient-vae-methodsKohaku-Blueleaf-32/+66
2023-08-05Reduce mask blur kernel size to 2.5 sigmasSplendide Imaginarius-2/+2
This more closely matches the old behavior of PIL's Gaussian blur, and fixes breakage when tiling. See https://github.com/Coyote-A/ultimate-upscale-for-automatic1111/issues/111#issuecomment-1663504109 Thanks to Алексей Трофимов and eunnone for reporting the issue.
2023-08-05Merge pull request #12181 from AUTOMATIC1111/hires_checkpointAUTOMATIC1111-31/+66
Hires fix change checkpoint
2023-08-05add infotextKohaku-Blueleaf-0/+3
2023-08-04replace get_first_stage_encodingKohaku-Blueleaf-7/+5
2023-08-04Revert "change all encode"Kohaku-Blueleaf-6/+8
This reverts commit 094c416a801b16c7d8e1944e2e9fae2c9e98bf12.
2023-08-04change all encodeKohaku-Blueleaf-8/+6
2023-08-04Merge branch 'dev' into efficient-vae-methodsKohaku-Blueleaf-7/+1
2023-08-04resolve some of circular import issues for kohakuAUTOMATIC1111-6/+1
2023-08-04add TAESD for i2i and t2iKohaku-Blueleaf-7/+6
2023-08-03Make StableDiffusionProcessingImg2Img.mask_blur a propertySplendide Imaginarius-3/+18
Fixes breakage when mask_blur is set after construction. See https://github.com/Coyote-A/ultimate-upscale-for-automatic1111/issues/111#issuecomment-1652091424 Thanks to Алексей Трофимов and eunnone for reporting the issue.
2023-08-03add NV option for Random number generator source setting, which allows to ↵AUTOMATIC1111-3/+3
generate same pictures on CPU/AMD/Mac as on NVidia videocards.
2023-08-02add yet another torch_gc to reclaim some of VRAM after the initial stage of ↵AUTOMATIC1111-0/+1
img2img
2023-07-31fix "clamp_scalar_cpu" not implemented for 'Half'AUTOMATIC1111-1/+1
generated by cgit v1.2.3 (git 2.39.1) at 2025-10-08 04:34:24 +0000