mirror/stable-diffusion-webui
2
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2024-12-21 07:30:02 +08:00
Code Issues Packages Projects Releases Wiki Activity
3,698 Commits 23 Branches 36 Tags 4.6 GiB
ac38ad7e60
Commit Graph

3698 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
AUTOMATIC1111
475095f50a
Merge pull request #7528 from spezialspezial/patch-1 
Catch broken model symlinks early | Quickfix modelloader.py
 2023-02-05 11:24:32 +03:00
AUTOMATIC
668d7e9b9a make it possible to load SD1 checkpoints without CLIP 2023-02-05 11:21:00 +03:00
techneconn
5a1b62e9f8 Add prompt_hash option for file/dir name pattern 2023-02-05 15:48:51 +09:00
Alex "mcmonkey" Goodwin
88a46e8427 fix symlinks in extra networks ui 
'absolute' and 'resolve' are equivalent, but 'resolve' resolves symlinks (which is an obscure specialty behavior usually not wanted) whereas 'absolute' treats symlinks as folders (which is the expected behavior). This commit allows you to symlink folders within your models/embeddings/etc. dirs and have preview images load as expected without issue.
 2023-02-04 09:10:00 -08:00
spezialspezial
6524478850
Update modelloader.py 
os.path.getmtime(filename) throws exception later in codepath when meeting broken symlink. For now catch it here early but more checks could be added for robustness.
 2023-02-04 16:52:15 +01:00
w-e-w
dd20fc0fda fix --help 
show correct help message
 2023-02-04 23:23:20 +09:00
AUTOMATIC
3e0f9a7543 fix issue with switching back to checkpoint that had its checksum calculated during runtime mentioned in #7506 2023-02-04 15:23:16 +03:00
AUTOMATIC
40e51fd6ef add margin parameter to draw_grid_annotations 2023-02-04 13:29:04 +03:00
AUTOMATIC1111
21593c8082
Merge pull request #7466 from ctwrs/master 
Add .jpg to allowed thumb formats
 2023-02-04 12:07:45 +03:00
AUTOMATIC1111
c0e0b5844d
Merge pull request #7470 from cbrownstein-lambda/update-error-message-no-checkpoint 
Update error message WRT missing checkpoint file
 2023-02-04 12:07:12 +03:00
AUTOMATIC1111
dca632ab90
Merge pull request #7509 from mezotaken/fix-img2imgalt 
Fix img2imgalt after samplers separation
 2023-02-04 11:41:29 +03:00
AUTOMATIC
81823407d9 add --no-hashing 2023-02-04 11:38:56 +03:00
AUTOMATIC1111
30228c67ca
Merge pull request #7461 from brkirch/mac-fixes 
Move Mac related code to separate file
 2023-02-04 11:22:52 +03:00
AUTOMATIC
c4b9ed1a27 make Image CFG Scale only show if instrutpix2pix model is loaded 2023-02-04 11:18:44 +03:00
AUTOMATIC
72dd5785d9 merge CFGDenoiserEdit and CFGDenoiser into single object 2023-02-04 11:06:17 +03:00
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