aboutsummaryrefslogtreecommitdiff
path: root/modules/sd_samplers_kdiffusion.py
AgeCommit message (Collapse)Author
2023-08-10lintAUTOMATIC1111
2023-08-10return the line lost during the mergeAUTOMATIC1111
2023-08-10resolve merge issuesAUTOMATIC1111
2023-08-10Merge branch 'dev' into refinerAUTOMATIC1111
2023-08-08by request: fix tiled vae extensionAUTOMATIC1111
2023-08-08merge errorsAUTOMATIC1111
2023-08-08Merge branch 'dev' into refinerAUTOMATIC1111
2023-08-08put commonly used samplers on top, make DPM++ 2M Karras the default choiceAUTOMATIC1111
2023-08-08REMOVEAUTOMATIC1111
2023-08-08add CFG denoiser implementation for DDIM, PLMS and UniPC (this is the commit ↵AUTOMATIC1111
when you can run both old and new implementations to compare them)
2023-08-08split sd_samplers_kdiffusion into twoAUTOMATIC1111
2023-08-08Split history: mv temp modules/sd_samplers_kdiffusion.pyAUTOMATIC1111
2023-08-08Split history: mv modules/sd_samplers_kdiffusion.py tempAUTOMATIC1111
2023-08-06add infotextAUTOMATIC1111
add proper support for recalculating conds in k-diffusion samplers remove support for compvis samplers
2023-08-06lint!AUTOMATIC1111
2023-08-06initial refiner supportAUTOMATIC1111
2023-08-05Assume 0 = inf for s_tmaxcatboxanon
2023-08-05Read kdiffusion sigma params from optscatboxanon
2023-08-05Add sigma params to infotextcatboxanon
2023-08-04Add exponential scheduler for DPM-Solver++(2M) SDEcatboxanon
Better quality results than Karras. Related discussion: https://gist.github.com/crowsonkb/3ed16fba35c73ece7cf4b9a2095f2b78
2023-08-03add NV option for Random number generator source setting, which allows to ↵AUTOMATIC1111
generate same pictures on CPU/AMD/Mac as on NVidia videocards.
2023-07-29split the new sampler into a different fileAUTOMATIC1111
2023-07-29Split history: mv temp modules/sd_samplers_kdiffusion.pyAUTOMATIC1111
2023-07-29Split history: mv modules/sd_samplers_kdiffusion.py tempAUTOMATIC1111
2023-07-29Merge pull request #11850 from lambertae/restart_samplingAUTOMATIC1111
Restart sampling
2023-07-25fix progress bar & torchHijacklambertae
2023-07-20new restart schemelambertae
2023-07-20fix rufflambertae
2023-07-20 allow choise of restart_list & use karras from kdiffusionlambertae
2023-07-20restart-sampler with correct stepslambertae
2023-07-18code stylinglambertae
2023-07-18fix floating errorlambertae
2023-07-18remove useless headerlambertae
2023-07-18add restart samplerlambertae
2023-07-12SDXL supportAUTOMATIC1111
2023-07-11getting SD2.1 to run on SDXL repoAUTOMATIC1111
2023-06-27add missing infotext entry for the pad cond/uncond optionAUTOMATIC
2023-05-31Merge pull request #10638 from catboxanon/patch/revert-10586AUTOMATIC1111
Revert discarding penultimate sigma for DPM-Solver++(2M) SDE
2023-05-27updates for the noise schedule settingsAUTOMATIC
2023-05-24use Schedule instead of SchedKohaku-Blueleaf
2023-05-24improvementsKohaku-Blueleaf
See: https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/10649#issuecomment-1561047723
2023-05-24Use automatic instead of None/defaultKohaku-Blueleaf
2023-05-23Use type to determine if it is enableKohaku-Blueleaf
2023-05-23Use better way to implKohaku-Blueleaf
2023-05-23Better hint for userKohaku-Blueleaf
Co-authored-by: catboxanon <122327233+catboxanon@users.noreply.github.com>
2023-05-22Revert #10586catboxanon
2023-05-23use sigma_max/min in model if sigma_max/min is 0Kohaku-Blueleaf
2023-05-23Add error information for recursion errorKohaku-Blueleaf
2023-05-22remove not related codeKohaku-Blueleaf
2023-05-22Replace karras by k_diffusion, fix gen infoKohaku-Blueleaf
generated by cgit v1.2.1 (git 2.18.0) at 2025-05-30 03:55:30 +0000