michael/stable-diffusion-webui
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
3985 commits 1 branch 0 tags 29 MiB
Commit graph

3985 commits

This branch
This branch
All branches
Author SHA1 Message Date
brkirch
4306659c4d Remove unused code 2023-02-04 01:22:06 -05:00
AUTOMATIC1111
127bfb6c41
Merge pull request #7481 from Klace/master 
img2img instruct-pix2pix support
 2023-02-04 09:05:21 +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
Vladimir Repin
982295aee5 Fix img2imgalt after samplers separation 2023-02-04 01:50:38 +03:00
Kyle
3b2ad20ac1 Processing only, no CFGDenoiser change 
Allows instruct-pix2pix
 2023-02-02 19:19:45 -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
Cody Brownstein
fb97acef63 Update error message WRT missing checkpoint file 
The Safetensors format is also supported.
 2023-02-01 14:51:06 -08:00
ctwrs
92bae77b88 Add .jpg to allowed thumb formats 2023-02-01 22:28:39 +01:00
Francesco Manzali
5afd9e82c3 Use the real images size, not the process 
- Use the width/height of the first image in processed.images
- No more need for rounding in prompt_matrix
 2023-02-01 21:16:52 +01:00
brkirch
1b8af15f13 Refactor Mac specific code to a separate file 
Move most Mac related code to a separate file, don't even load it unless web UI is run under macOS.
 2023-02-01 14:05:56 -05:00
AUTOMATIC1111
226d840e84
Merge pull request #7334 from EllangoK/master 
X/Y/Z plot now saves sub grids if opts.grid_save and honors draw_legend
 2023-02-01 16:30:28 +03:00
AUTOMATIC1111
07edf57409
Merge pull request #7357 from EllangoK/btn-fix 
Fixes switch height/width btn unbound error
 2023-02-01 16:29:58 +03:00
AUTOMATIC1111
fa4fe45403
Merge pull request #7371 from hoblin/master 
[Prompt Matrix] Support for negative prompt + delimiter selector
 2023-02-01 16:28:27 +03:00
AUTOMATIC1111
814600f298
Merge pull request #7412 from Pomierski/master 
Fix missing tooltip for 'Clear prompt' button
 2023-02-01 16:22:36 +03:00
AUTOMATIC1111
30a64504b1
Merge pull request #7414 from joecodecreations/master 
Changes use_original_name_batch to default to True
 2023-02-01 16:22:16 +03:00
AUTOMATIC1111
b1873dbb77
Merge pull request #7455 from brkirch/put-fix-back 
Refactor MPS PyTorch fixes, add fix still required for PyTorch nightly builds back
 2023-02-01 16:11:40 +03:00
brkirch
2217331cd1 Refactor MPS fixes to CondFunc 2023-02-01 06:36:22 -05:00
brkirch
7738c057ce MPS fix is still needed :( 
Apparently I did not test with large enough images to trigger the bug with torch.narrow on MPS
 2023-02-01 05:23:58 -05:00
Francesco Manzali
17b24e45e8 Fix prompt matrix #rows/#cols when using hires 
- images.draw_prompt_matrix() should be called with the final width/height
  of the generated images, after upscaling.
  Otherwise, the number of rows/cols computed in images.draw_grid_annotations
  will increase by the upscaling factor.
- Round the number of cols/rows in images.draw_grid_annotations, since
  the final images width may be a bit less than the required
  hr_upscale_to_x/y
 2023-01-31 18:58:36 +01:00
Joey Sanchez
0426b34789 Adding default true to use_original_name_batch as images should by default hold the same name to help keep sequenced images in their correct order 2023-01-30 21:46:52 -05:00
Piotr Pomierski
bfe7e7f15f Fix missing tooltip for 'Clear prompt' button 2023-01-31 01:51:07 +01:00
AUTOMATIC
2c1bb46c7a amend the error in previous commit 2023-01-30 18:48:10 +03:00
AUTOMATIC
19de2a626b make linux launch.py use XFORMERS_PACKAGE var too; thanks, acncagua 2023-01-30 15:48:09 +03:00
AUTOMATIC
ee9fdf7f62 Add --skip-version-check to disable messages asking users to upgrade torch. 2023-01-30 14:56:28 +03:00
AUTOMATIC
aa4688eb83 disable EMA weights for instructpix2pix model, whcih should get memory usage as well as image quality to what it was before d2ac95fa7b 2023-01-30 13:29:44 +03:00
AUTOMATIC
ab059b6e48 make the program read Discard penultimate sigma from generation parameters 2023-01-30 10:52:15 +03:00
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
274474105a Split history sd_samplers.py to sd_samplers_kdiffusion.py 2023-01-30 09:51:23 +03:00
Andrey
95916e3777 Split history sd_samplers.py to sd_samplers_kdiffusion.py 2023-01-30 09:51:23 +03:00
Andrey
2db8ed32cd Split history sd_samplers.py to sd_samplers_kdiffusion.py 2023-01-30 09:51:23 +03:00
Andrey
f4d0538bf2 Split history sd_samplers.py to sd_samplers_kdiffusion.py 2023-01-30 09:51:23 +03:00
AUTOMATIC
aa54a9d416 split compvis sampler and shared sampler stuff into their own files 2023-01-30 09:51:06 +03:00
Andrey
f8fcad502e Split history sd_samplers.py to sd_samplers_common.py 2023-01-30 09:37:51 +03:00
Andrey
58ae93b954 Split history sd_samplers.py to sd_samplers_common.py 2023-01-30 09:37:50 +03:00
Andrey
6e78f6a896 Split history sd_samplers.py to sd_samplers_common.py 2023-01-30 09:37:50 +03:00
Andrey
5feae71dd2 Split history sd_samplers.py to sd_samplers_common.py 2023-01-30 09:37:50 +03:00
Andrey
449531a6c5 Split history sd_samplers.py to sd_samplers_compvis.py 2023-01-30 09:35:53 +03:00
Andrey
9b8ed7f8ec Split history sd_samplers.py to sd_samplers_compvis.py 2023-01-30 09:35:53 +03:00
Andrey
9118b08606 Split history sd_samplers.py to sd_samplers_compvis.py 2023-01-30 09:35:52 +03:00
Andrey
0c7c36a6c6 Split history sd_samplers.py to sd_samplers_compvis.py 2023-01-30 09:35:52 +03:00
AUTOMATIC
cbd6329488 add an environment variable for selecting xformers package 2023-01-30 09:12:43 +03:00
AUTOMATIC
c81b52ffbd add override settings component to img2img 2023-01-30 02:40:26 +03:00
AUTOMATIC
847ceae1f7 make it possible to search checkpoint by its hash 2023-01-30 01:41:23 +03:00
AUTOMATIC
399720dac2 update prompt token counts after using the paste params button 2023-01-30 01:03:31 +03:00
AUTOMATIC
f91068f426 change disable_weights_auto_swap to true by default 2023-01-30 00:37:26 +03:00
AUTOMATIC
938578e8a9 make it so that setting options in pasted infotext (like Clip Skip and ENSD) do not get applied directly and instead are added as temporary overrides 2023-01-30 00:25:30 +03:00