Commit Graph

109 Commits

Author SHA1 Message Date
AUTOMATIC1111 9aa9e980a9 support scheduler selection in hires fix 2024-03-24 11:00:16 +03:00
AUTOMATIC1111 31306ce672 change the behavior of discard_next_to_last_sigma for sgm_uniform to match other schedulers 2024-03-20 10:29:52 +03:00
AUTOMATIC1111 ac9aa44cb8 do not add 'Automatic' to infotext 2024-03-20 10:27:53 +03:00
AUTOMATIC1111 25cd53d775 scheduler selection in main UI 2024-03-20 09:17:11 +03:00
Kohaku-Blueleaf a6b5a513f9 Implementation for sgm_uniform branch 2024-03-19 20:05:54 +08:00
AUTOMATIC1111 757dda9ade Add Pad conds v0 option 2024-01-27 22:30:47 +03:00
catboxanon 549b475be9 Add noisy latent to ExtraNoiseParams for callback 2023-08-29 14:22:04 -04:00
AUTOMATIC1111 04b90328c0 revert SGM noise multiplier change for img2img because it breaks hires fix 2023-08-29 15:38:33 +03:00
catboxanon 7ab16e99ee Add option to align with sgm repo sampling implementation 2023-08-29 01:51:13 -04:00
catboxanon 254be4eeb2 Add extra noise callback 2023-08-16 21:45:19 -04:00
catboxanon 371b24b17c Add extra img2img noise 2023-08-15 02:19:19 -04:00
AUTOMATIC1111 6bfd4dfecf add second_order to samplers that mistakenly didn't have it 2023-08-14 12:07:38 +03:00
Kohaku-Blueleaf aa26f8eb40 Put frequently used sampler back 2023-08-14 13:50:53 +08:00
Kohaku-Blueleaf 0ea61a74be add res(dpmdd 2m sde heun) and reorder the sampler list 2023-08-14 11:46:36 +08:00
AUTOMATIC1111 d41a5bb97d
Merge pull request #12521 from catboxanon/feat/more-s-noise
Add `s_noise` param to more samplers
2023-08-13 16:39:25 +03:00
catboxanon 525b55b1e9 Restore extra_params that was lost in merge 2023-08-13 09:08:34 -04:00
catboxanon ce0829d711 Merge branch 'feat/dpmpp3msde' into feat/more-s-noise 2023-08-13 08:46:58 -04:00
catboxanon ac790fc49b Discard penultimate sigma for DPM-Solver++(3M) SDE 2023-08-13 08:46:07 -04:00
catboxanon d1a70c3f05 Add s_noise param to more samplers 2023-08-13 08:22:24 -04:00
catboxanon 1ae9dacb4b Add DPM-Solver++(3M) SDE 2023-08-13 07:57:29 -04:00
AUTOMATIC1111 64311faa68 put refiner into main UI, into the new accordions section
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
2023-08-12 12:39:59 +03:00
AUTOMATIC1111 4549f2a9cc lint 2023-08-10 17:21:01 +03:00
AUTOMATIC1111 f4979422dd return the line lost during the merge 2023-08-10 17:18:33 +03:00
AUTOMATIC1111 ac8a5d18d3 resolve merge issues 2023-08-10 17:04:59 +03:00
AUTOMATIC1111 70a01cd444 Merge branch 'dev' into refiner 2023-08-10 17:04:38 +03:00
AUTOMATIC1111 0e83c67525 by request: fix tiled vae extension 2023-08-08 22:27:32 +03:00
AUTOMATIC1111 f8ff8c0638 merge errors 2023-08-08 22:09:51 +03:00
AUTOMATIC1111 54c3e5c913 Merge branch 'dev' into refiner 2023-08-08 21:49:47 +03:00
AUTOMATIC1111 ae1bde1aa1 put commonly used samplers on top, make DPM++ 2M Karras the default choice 2023-08-08 21:10:12 +03:00
AUTOMATIC1111 a8a256f9b5 REMOVE 2023-08-08 21:08:50 +03:00
AUTOMATIC1111 8285a149d8 add CFG denoiser implementation for DDIM, PLMS and UniPC (this is the commit when you can run both old and new implementations to compare them) 2023-08-08 21:04:44 +03:00
AUTOMATIC1111 2d8e4a6544 split sd_samplers_kdiffusion into two 2023-08-08 18:35:31 +03:00
AUTOMATIC1111 c721884cf5 Split history: mv temp modules/sd_samplers_kdiffusion.py 2023-08-08 18:32:18 +03:00
AUTOMATIC1111 a3e27019e4 Split history: mv modules/sd_samplers_kdiffusion.py temp 2023-08-08 18:32:17 +03:00
AUTOMATIC1111 5a0db84b6c add infotext
add proper support for recalculating conds in k-diffusion samplers
remove support for compvis samplers
2023-08-06 17:53:33 +03:00
AUTOMATIC1111 956e69bf3a lint! 2023-08-06 17:07:08 +03:00
AUTOMATIC1111 f1975b0213 initial refiner support 2023-08-06 17:01:07 +03:00
catboxanon 8f31b139b8 Assume 0 = inf for s_tmax 2023-08-05 23:50:33 -04:00
catboxanon ce4be668fe Read kdiffusion sigma params from opts 2023-08-05 23:42:20 -04:00
catboxanon 31506f0771 Add sigma params to infotext 2023-08-05 22:37:25 -04:00
catboxanon 3bd2c68eb4
Add exponential scheduler for DPM-Solver++(2M) SDE
Better quality results than Karras.
Related discussion: https://gist.github.com/crowsonkb/3ed16fba35c73ece7cf4b9a2095f2b78
2023-08-04 00:51:49 -04:00
AUTOMATIC1111 84b6fcd02c add NV option for Random number generator source setting, which allows to generate same pictures on CPU/AMD/Mac as on NVidia videocards. 2023-08-03 00:00:23 +03:00
AUTOMATIC1111 aefe1325df split the new sampler into a different file 2023-07-29 08:11:59 +03:00
AUTOMATIC1111 11dc92dc0a Split history: mv temp modules/sd_samplers_kdiffusion.py 2023-07-29 08:06:04 +03:00
AUTOMATIC1111 e1323fc1b7 Split history: mv modules/sd_samplers_kdiffusion.py temp 2023-07-29 08:06:03 +03:00
AUTOMATIC1111 bef40851af
Merge pull request #11850 from lambertae/restart_sampling
Restart sampling
2023-07-29 08:03:32 +03:00
lambertae 8de6d3ff77 fix progress bar & torchHijack 2023-07-25 22:35:43 -04:00
lambertae f873890298 new restart scheme 2023-07-20 21:27:43 -04:00
lambertae 128d59c9cc fix ruff 2023-07-20 20:36:40 -04:00
lambertae 2f57a559ac allow choise of restart_list & use karras from kdiffusion 2023-07-20 20:34:41 -04:00