aboutsummaryrefslogtreecommitdiffstats
path: root/modules/processing.py
AgeCommit message (Collapse)AuthorLines
2024-02-19Merge pull request #14966 from light-and-ray/avoid_doble_upscaling_in_inpaintAUTOMATIC1111-9/+6
[bug] avoid doble upscaling in inpaint
2024-02-11add infotext entry for emphasis; put emphasis into a separate file, add an ↵AUTOMATIC1111-0/+1
option to parse but still ignore emphasis
2024-01-23add an option to not overlay original image for inpainting for #14727AUTOMATIC1111-1/+7
2024-01-21improve get_crop_regionw-e-w-1/+1
2024-01-20Merge pull request #14657 from ↵AUTOMATIC1111-0/+5
AUTOMATIC1111/callback-postprocess_image_after_composite callback postprocess_image_after_composite
2024-01-18fix console total progress bar when using txt2img_upscalew-e-w-2/+5
add p.txt2img_upscale as indicator
2024-01-16callback postprocess_image_after_compositew-e-w-0/+5
2024-01-05Make the upscale button update the gallery with the new image rather than ↵AUTOMATIC1111-1/+5
replace it.
2024-01-02fix #14497AUTOMATIC1111-0/+13
2024-01-01added a button to run hires fix on selected image in the galleryAUTOMATIC1111-9/+37
2024-01-01rename infotext.py again, this time to infotext_utils.py; I didn't realize ↵AUTOMATIC1111-2/+2
infotext would be used for variable names in multiple places, which makes it awkward to import the module; also fix the bug I caused by this rename that breaks tests
2024-01-01fix borked merge, rename fields to better match what they do, change setting ↵AUTOMATIC1111-1/+1
default to true for #13653
2024-01-01Merge branch 'dev' into feat/interrupted-endAUTOMATIC1111-56/+160
2024-01-01option to convert VAE to bfloat16 (implementation of #9295)AUTOMATIC1111-5/+18
2024-01-01Merge pull request #14145 from drhead/zero-terminal-snrAUTOMATIC1111-0/+28
Implement zero terminal SNR noise schedule option
2024-01-01infotext.py: rename usages in the codebaseAUTOMATIC1111-2/+2
2023-12-30Merge pull request #14390 from wangqyqq/sdxl-inpaintAUTOMATIC1111-0/+21
Supporting for SDXL-Inpaint Model
2023-12-30Merge pull request #14452 from AUTOMATIC1111/save-info-of-init-imageAUTOMATIC1111-1/+1
save info of init image
2023-12-30aAUTOMATIC1111-1/+1
2023-12-29save info of init imagew-e-w-1/+1
2023-12-27add some codes for robustwangqyqq-11/+13
2023-12-21support for sdxl-inpaint modelwangqyqq-0/+19
2023-12-16Let fp8-related settings to invalidate cond_cacheKohaku-Blueleaf-0/+2
2023-12-16Merge pull request #14314 from gayshub/masterAUTOMATIC1111-0/+2
Add allow specify the task id and get the location of task in the queue of pending task
2023-12-16Add FP8 settings into PNG infoKohaku-Blueleaf-0/+2
2023-12-15fix the problem of ruff of githubgayshub-1/+1
2023-12-15add allow specify the task id and get the location of task in the queue of ↵gayshub-0/+2
pending task
2023-12-07Fixed error that occurs when using vanilla samplers (somehow).CodeHatchling-2/+2
2023-12-07Re-implemented soft inpainting via a script. Also fixed some mistakes with ↵CodeHatchling-13/+10
the previous hooks, removed unnecessary formatting changes, removed code that I had forgotten to.
2023-12-06Removed soft inpainting, added hooks for softpainting to work instead.CodeHatchling-56/+38
2023-12-04Merge remote-tracking branch 'origin2/dev' into soft-inpaintingCodeHatchling-18/+17
# Conflicts: # modules/processing.py
2023-12-04Fixed unused import.CodeHatchling-1/+1
2023-12-04Fixed issue where batched inpainting (batch size > 1) wouldn't work because ↵CodeHatchling-8/+15
of mismatched tensor sizes. The 'already_decoded' decoded case should also be handled correctly (tested indirectly).
2023-12-04Applies a convert('RGBA') operation early to mimic previous behaviour.CodeHatchling-1/+1
2023-12-04Restored original formatting.CodeHatchling-25/+11
2023-12-04Re-introduce latent blending step from the vanilla inpainting procedure.CodeHatchling-0/+3
2023-12-04Cleaned up code, moved main code contributions into soft_inpainting.pyCodeHatchling-49/+7
2023-12-04Enables the original functionality to be toggled on and off.CodeHatchling-29/+70
2023-12-04Organized the settings and UI of soft inpainting to allow for toggling the ↵CodeHatchling-3/+2
feature, and centralizes default values to reduce the amount of copy-pasta.
2023-12-03"Uncrop" the original denoised image for the composite step, fixing a ↵CodeHatchling-0/+4
"ValueError: Images do not match" *shudder*
2023-12-03rework mask and mask_composite logicw-e-w-15/+14
2023-12-02Merge remote-tracking branch 'origin/dev' into soft-inpaintingCodeHatchling-10/+10
# Conflicts: # modules/processing.py
2023-12-02Blend masks are now produced afterward, based on an estimate of the visual ↵CodeHatchling-29/+90
difference between the original and modified latent images. This should remove ghosting and clipping artifacts from masks, while preserving the details of largely unchanged content.
2023-12-02Revert 309a606cdrhead-11/+9
2023-12-02Fix `save_samples` being checked early when saving masked compositecatboxanon-3/+3
2023-12-02fix lintingdrhead-1/+1
2023-12-02ensure that original alpha bar always existsdrhead-9/+11
2023-12-02infotext updates: add option to disregard certain infotext fields, add ↵AUTOMATIC1111-2/+2
option to not include VAE in infotext, add explanation to infotext settings page, move some options to infotext settings page
2023-11-29remove debug printdrhead-1/+0
2023-11-29Only apply ztSNR related code if alphas_cumprod existscatboxanon-9/+10
generated by cgit v1.2.3 (git 2.39.1) at 2025-10-07 18:27:39 +0000