Commit Graph

109 Commits

Author SHA1 Message Date
lambertae ddbf4a73f5 restart-sampler with correct steps 2023-07-20 02:24:18 -04:00
lambertae 7bb0fbed13 code styling 2023-07-18 01:02:04 -04:00
lambertae 37e048a7e2 fix floating error 2023-07-18 00:55:02 -04:00
lambertae 15a94d6cf7 remove useless header 2023-07-18 00:39:26 -04:00
lambertae 40a18d38a8 add restart sampler 2023-07-18 00:32:01 -04:00
AUTOMATIC1111 da464a3fb3 SDXL support 2023-07-12 23:52:43 +03:00
AUTOMATIC1111 af081211ee getting SD2.1 to run on SDXL repo 2023-07-11 21:16:43 +03:00
AUTOMATIC 4bd490c28d add missing infotext entry for the pad cond/uncond option 2023-06-27 06:18:43 +03:00
AUTOMATIC1111 e72013ea67
Merge pull request #10638 from catboxanon/patch/revert-10586
Revert discarding penultimate sigma for DPM-Solver++(2M) SDE
2023-05-31 19:34:20 +03:00
AUTOMATIC e8e7fe11e9 updates for the noise schedule settings 2023-05-27 19:53:09 +03:00
Kohaku-Blueleaf a69b71a37f use Schedule instead of Sched 2023-05-24 20:40:37 +08:00
Kohaku-Blueleaf 4b88e24ebe improvements
See:
https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/10649#issuecomment-1561047723
2023-05-24 20:35:58 +08:00
Kohaku-Blueleaf 1601fccebc Use automatic instead of None/default 2023-05-24 00:18:09 +08:00
Kohaku-Blueleaf 72377b0251 Use type to determine if it is enable 2023-05-23 23:48:23 +08:00
Kohaku-Blueleaf 70650f87a4 Use better way to impl 2023-05-23 11:34:51 +08:00
Kohaku-Blueleaf 38aaad654b
Better hint for user
Co-authored-by: catboxanon <122327233+catboxanon@users.noreply.github.com>
2023-05-23 09:38:30 +08:00
catboxanon 51d672890d
Revert #10586 2023-05-22 13:06:57 -04:00
Kohaku-Blueleaf 403b304162 use sigma_max/min in model if sigma_max/min is 0 2023-05-23 00:29:38 +08:00
Kohaku-Blueleaf 65a87ccc9b Add error information for recursion error 2023-05-23 00:09:49 +08:00
Kohaku-Blueleaf 5dfb1f597b remove not related code 2023-05-22 23:36:16 +08:00
Kohaku-Blueleaf 7882f76da4 Replace karras by k_diffusion, fix gen info 2023-05-22 23:26:28 +08:00
Kohaku-Blueleaf e6269cba7f Add dropdown for scheduler type 2023-05-22 23:02:05 +08:00
Kohaku-Blueleaf 90ec557d60 remove debug print 2023-05-22 22:06:13 +08:00
Kohaku-Blueleaf a104879869 Add custom karras scheduler 2023-05-22 21:52:46 +08:00
AUTOMATIC 3366e494a1 option to pad prompt/neg prompt to be same length 2023-05-22 00:13:53 +03:00
catboxanon 9a442702d1
Discard penultimate sigma for dpmpp_2m_sde 2023-05-21 01:01:59 -04:00
AUTOMATIC 31545abe14 add DPM-Solver++(2M) SDE from new k-diffusion 2023-05-21 07:31:51 +03:00
AUTOMATIC a61cbef02c add second_order field to sampler config 2023-05-16 12:36:15 +03:00
AUTOMATIC cdac5ace14 suppress ENSD infotext for samplers that don't use it 2023-05-16 11:54:02 +03:00
AUTOMATIC 005849331e remove output_altered flag from AfterCFGCallbackParams 2023-05-14 08:15:22 +03:00
catboxanon 3078001439 Add/modify CFG callbacks
Required by self-attn guidance extension
https://github.com/ashen-sensored/sd_webui_SAG
2023-05-14 01:49:41 +00:00
Aarni Koskela 49a55b410b Autofix Ruff W (not W605) (mostly whitespace) 2023-05-11 20:29:11 +03:00
AUTOMATIC 028d3f6425 ruff auto fixes 2023-05-10 11:05:02 +03:00
AUTOMATIC f741a98bac imports cleanup for ruff 2023-05-10 08:43:42 +03:00
Aarni Koskela 3ba6c3c83c Fix up string formatting/concatenation to f-strings where feasible 2023-05-09 22:25:39 +03:00
AUTOMATIC 8863b31d83 use correct images for previews when using AND (see #9491) 2023-04-29 16:06:20 +03:00
AUTOMATIC 737b73a820 some extra lines I forgot to add for previous commit 2023-04-29 16:05:20 +03:00
AUTOMATIC 1d11e89698 rework Negative Guidance minimum sigma to work with AND, add infotext and copypaste parameters support 2023-04-29 15:57:09 +03:00
AUTOMATIC1111 3591eefedf
Merge pull request #9177 from devNegative-asm/master
(Optimization) Option to remove negative conditioning at low sigma values
2023-04-29 14:38:25 +03:00
AUTOMATIC 5fe0dd79be rename CPU RNG to RNG source in settings, add infotext and parameters copypaste support to RNG source 2023-04-29 11:29:37 +03:00
Deciare d40e44ade4 Option to use CPU for random number generation.
Makes a given manual seed generate the same images across different
platforms, independently of the GPU architecture in use.

Fixes #9613.
2023-04-18 23:27:46 -04:00
devdn 44e8e9c368 fix live preview & alternate uncond guidance for better quality 2023-03-30 00:54:28 -04:00
devdn 42082e8a32 performance increase 2023-03-28 20:56:01 -04:00
MrCheeze 8a34671fe9 Add support for the Variations models (unclip-h and unclip-l) 2023-03-25 21:03:07 -04:00
AUTOMATIC 7f2005127f rename CFGDenoiserParams fields for #8064 2023-03-11 14:52:29 +03:00
laksjdjf 9a1435946c
Update sd_samplers_kdiffusion.py 2023-02-24 14:04:23 +09:00
AUTOMATIC1111 3fcc087317
Merge pull request #7731 from opparco/master
Add cfg_denoised_callback
2023-02-19 11:09:47 +03:00
RcINS f55a7e04d8 Fix error when batch count > 1 2023-02-15 16:57:18 +08:00
opparco b78c5e87ba Add cfg_denoised_callback 2023-02-11 11:18:38 +09:00
RcINS 9e27af76d1 Fix DPM++ SDE not deterministic across different batch sizes (#5210) 2023-02-11 10:12:16 +08:00
AUTOMATIC 72dd5785d9 merge CFGDenoiserEdit and CFGDenoiser into single object 2023-02-04 11:06:17 +03:00
Kyle ba6a4e7e94 Use original CFGDenoiser if image_cfg_scale = 1
If image_cfg_scale is =1 then the original image is not used for the output. We can then use the original CFGDenoiser to get the same result to support AND functionality.

Maybe in the future AND can be supported with "Image CFG Scale"
2023-02-03 19:46:13 -05:00
Kyle c27c0de0f7 txt2img Hires Fix 2023-02-03 19:15:32 -05:00
Kyle 6c6c6636bb Image CFG Added (Full Implementation)
Uses separate denoiser for edit (instruct-pix2pix) models

No impact to txt2img or regular img2img

"Image CFG Scale" will only apply to instruct-pix2pix models and metadata will only be added if using such model
2023-02-03 18:19:56 -05:00
Kyle cf0cfefe91 Revert "instruct-pix2pix support"
This reverts commit 269833067d.
2023-02-02 19:15:38 -05:00
Kyle 269833067d instruct-pix2pix support 2023-02-02 09:37:01 -05:00
AUTOMATIC 040ec7a80e make the program read Eta and Eta DDIM from generation parameters 2023-01-30 10:47:09 +03:00
AUTOMATIC 4df63d2d19 split samplers into one more files for k-diffusion 2023-01-30 10:11:30 +03:00
Andrey f4d0538bf2 Split history sd_samplers.py to sd_samplers_kdiffusion.py 2023-01-30 09:51:23 +03:00