aboutsummaryrefslogtreecommitdiffstats
path: root/modules/processing.py
AgeCommit message (Collapse)AuthorLines
2022-12-24add an option for img2img background colorAUTOMATIC-1/+1
2022-12-20feat(api): add override_settings_restore_afterwardsPhilpax-13/+16
2022-12-14Fix various typosJim Hays-7/+7
2022-12-13Save hypernetwork hash in infotextspace-nuko-2/+3
2022-12-11Improve color correction with luminosity blendThereforeGames-3/+6
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
2022-12-10remove NSFW filter and its dependency; if you still want it, find it in the ↵AUTOMATIC-4/+3
extensions section
2022-12-10add Noise multiplier option to infotextAUTOMATIC-2/+6
2022-12-10Merge pull request #5373 from mezotaken/masterAUTOMATIC1111-0/+1
add noise strength parameter similar to NAI
2022-12-08Depth2img model supportJay Smith-4/+34
2022-12-08Add latent upscale option to img2imgAndrew Ryan-1/+5
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
2022-12-03add noise strength parameter similar to NAIVladimir Repin-0/+1
2022-12-03Merge pull request #5251 from adieyal/bug/negative-prompt-infotextAUTOMATIC1111-1/+1
Fixed incorrect negative prompt text in infotext
2022-11-30Fixed incorrect negative prompt text in infotextAdi Eyal-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
2022-11-29Support changing checkpoint and vae through override_settingsBilly Cao-2/+8
2022-11-28Make VAE step sequential to prevent VRAM spikesklimaleksus-2/+2
2022-11-27fix for broken sampler selection in img2img and xy plot #4860 #4909AUTOMATIC-1/+1
2022-11-20Merge pull request #4120 from aliencaocao/enable-override-hypernetAUTOMATIC1111-2/+4
Enable override_settings to take effect for hypernetworks
2022-11-19prevent StableDiffusionProcessingImg2Img changing image_mask field as an ↵AUTOMATIC-17/+16
alternative solution to #4765
2022-11-19make it possible for StableDiffusionProcessing to accept multiple different ↵AUTOMATIC-22/+24
negative prompts in a batch
2022-11-19Merge pull request #4778 from leppie/fix_unbounded_prompt_growthAUTOMATIC1111-0/+5
Fix unbounded prompt growth/determinism in scripts that loop
2022-11-19renamed Inpainting strength infotext to Conditional mask weight, made it ↵AUTOMATIC-1/+8
only appear if using inpainting model, made it possible to read the setting from it using the blue arrow button
2022-11-19Merge pull request #4679 from Eugenii10/inpaint-strength-to-infotextAUTOMATIC1111-0/+1
Add 'Inpainting strength' to the 'generation_params' of 'infotext' (params.txt or png chunks)
2022-11-19change StableDiffusionProcessing to internally use sampler name instead of ↵AUTOMATIC-17/+12
sampler index
2022-11-16Fix unbounded prompt growth scripts that loopLlewellyn Pritchard-0/+5
2022-11-14Fix retrieving value for 'x/y plot' script.KEV-1/+1
2022-11-14Add 'Inpainting strength' to the 'generation_params' dictionary of ↵KEV-0/+1
'infotext' which is saved into the 'params.txt' or png chunks. Value appears only if 'Denoising strength' appears too.
2022-11-06Merge branch 'master' into enable-override-hypernetBilly Cao-23/+40
2022-11-06Resolve conflictBilly Cao-2/+2
2022-11-04change process_one virtual function for script to process_batch, add extra ↵AUTOMATIC-1/+1
args and docs
2022-11-04Merge pull request #4182 from macrosoft/process_oneAUTOMATIC1111-0/+3
Process one
2022-11-04bugfix: save image for hires fix BEFORE upscaling latent spaceAUTOMATIC-4/+4
2022-11-04move option access checking to options class out of various places scattered ↵AUTOMATIC-2/+2
through code
2022-11-03Merge branch 'AUTOMATIC1111:master' into masterrandom-thoughtss-6/+24
2022-11-02add number of itterArtem Zagidulin-1/+1
2022-11-02process_oneArtem Zagidulin-0/+3
2022-11-02do not unnecessarily run VAE one more time when saving intermediate image ↵AUTOMATIC-19/+20
with hires fix
2022-11-02Allow saving "before-highres-fix. (#4150)timntorres-2/+15
* Save image/s before doing highres fix.
2022-11-01Release processing resources after it finishesJairo Correa-3/+4
2022-11-01Enable override_settings to take effect for hypernetworksBilly Cao-2/+4
2022-11-01Unload sd_model before loading the otherJairo Correa-0/+3
2022-10-30Replaced master branch fix with updated fix.random_thoughtss-2/+0
2022-10-30Merge branch 'AUTOMATIC1111:master' into masterrandom-thoughtss-3/+12
2022-10-30shorten Hypernetwork strength in infotext and omit it when it's the default ↵AUTOMATIC-1/+1
value.
2022-10-30Merge pull request #3831 from timntorres/3825-save-hypernet-strength-to-infoAUTOMATIC1111-0/+1
Save Hypernetwork strength to infotext.
2022-10-30fix broken hires fixAUTOMATIC-5/+2
2022-10-29Merge commit 'e7254746bbfbff45099db44a8d4d25dd6181877d' into ↵timntorres-3/+9
3825-save-hypernet-strength-to-info
2022-10-29Re-add explicit device moverandom_thoughtss-0/+1
2022-10-29add postprocess call for scriptsAUTOMATIC-3/+9
2022-10-29Added image conditioning to latent upscale.random_thoughtss-18/+11
Only comuted if the mask weight is not 1.0 to avoid extra memory. Also includes some code cleanup.
generated by cgit v1.2.3 (git 2.39.1) at 2025-10-08 01:13:53 +0000