brkirch
|
3bfe2bb549
|
Merge remote-tracking branch 'upstream/master' into sub-quad_attn_opt
|
3 years ago |
|
brkirch
|
f6ab5a39d7
|
Merge branch 'AUTOMATIC1111:master' into sub-quad_attn_opt
|
3 years ago |
|
brkirch
|
d782a95967
|
Add Birch-san's sub-quadratic attention implementation
|
3 years ago |
AUTOMATIC
|
99b67cff0b
|
make hires fix not do anything if the user chooses the second pass resolution to be the same as first pass resolution
|
3 years ago |
|
AUTOMATIC
|
bc43293c64
|
fix incorrect display/calculation for number of steps for hires fix in progress bars
|
3 years ago |
|
AUTOMATIC
|
8149078094
|
added the option to specify target resolution with possibility of truncating for hires fix; also sampling steps
|
3 years ago |
|
AUTOMATIC
|
24d4a0841d
|
train tab visual updates
allow setting train tab values from ui-config.json
|
3 years ago |
|
AUTOMATIC1111
|
eeb1de4388
|
Merge branch 'master' into gradient-clipping
|
3 years ago |
|
AUTOMATIC1111
|
e9911391ca
|
Merge pull request #6305 from vladmandic/fix-jpeg
fix jpeg handling
|
3 years ago |
|
AUTOMATIC
|
097a90b88b
|
add XY plot parameters to grid image and do not add them to individual images
|
3 years ago |
|
AUTOMATIC
|
3dae545a03
|
rename weirdly named variables from #3176
|
3 years ago |
|
AUTOMATIC1111
|
37aafdb059
|
Merge branch 'master' into master
|
3 years ago |
|
AUTOMATIC
|
a8eb9e3bf8
|
Revert "Merge pull request #3791 from shirayu/fix/filename"
This reverts commit eed58279e7, reversing
changes made to 4ae960b01c.
|
3 years ago |
|
AUTOMATIC1111
|
eed58279e7
|
Merge pull request #3791 from shirayu/fix/filename
Truncate too long filename (Fix #705)
|
3 years ago |
|
AUTOMATIC
|
525cea9245
|
use shared function from processing for creating dummy mask when training inpainting model
|
3 years ago |
Vladimir Mandic
|
590c5ae016
|
update pillow
|
3 years ago |
|
AUTOMATIC
|
184e670126
|
fix the merge
|
3 years ago |
|
AUTOMATIC1111
|
da5c1e8a73
|
Merge branch 'master' into inpaint_textual_inversion
|
3 years ago |
|
AUTOMATIC1111
|
47df084901
|
Merge pull request #6304 from vladmandic/add-cross-attention-info
add cross-attention info
|
3 years ago |
|
AUTOMATIC
|
4d66bf2c0d
|
add infotext to "-before-highres-fix" images
|
3 years ago |
|
Vladimir Mandic
|
79c682ad4f
|
fix jpeg
|
3 years ago |
|
AUTOMATIC
|
1cfd8aec4a
|
make it possible to work with opts.show_progress_every_n_steps = -1 with medvram
|
3 years ago |
|
Vladimir Mandic
|
21ee77db31
|
add cross-attention info
|
3 years ago |
|
AUTOMATIC1111
|
c923de0e05
|
Merge pull request #5969 from philpax/include-job-timestamp-in-progress-api
feat(api): include job_timestamp in progress
|
3 years ago |
|
AUTOMATIC
|
642142556d
|
use commandline-supplied cuda device name instead of cuda:0 for safetensors PR that doesn't fix anything
|
3 years ago |
|
AUTOMATIC
|
68fbf4558f
|
Merge remote-tracking branch 'Narsil/fix_safetensors_load_speed'
|
3 years ago |
|
Vladimir Mandic
|
11b8160a08
|
fix typo
|
3 years ago |
|
AUTOMATIC
|
0cd6399b8b
|
fix broken inpainting model
|
3 years ago |
|
AUTOMATIC
|
3bd737767b
|
disable broken API logging
|
3 years ago |
|
AUTOMATIC1111
|
7bbd984dda
|
Merge pull request #6253 from Shondoit/ti-optim
Save Optimizer next to TI embedding
|
3 years ago |
|
AUTOMATIC1111
|
545ae8cb1c
|
Merge pull request #6264 from vladmandic/add-state-info
add missing state info
|
3 years ago |
|
AUTOMATIC1111
|
a8ad8666cd
|
Merge pull request #6261 from vladmandic/api-logging
add api logging
|
3 years ago |
|
AUTOMATIC1111
|
6281c1bdb4
|
Merge pull request #6299 from stysmmaker/feat/latent-upscale-modes
Add more latent upscale modes
|
3 years ago |
|
AUTOMATIC1111
|
77c3bc7747
|
Merge pull request #6298 from stysmmaker/fix/intermediate-step-full-res
Save full resolution of intermediate step
|
3 years ago |
MMaker
|
b2151b934f
|
Rename bicubic antialiased option
Comma was causing the the value in PNG info to be quoted, which causes the upscaler dropdown option to be blank when sending to UI
|
3 years ago |
MMaker
|
f49f917cdd
|
Merge branch 'AUTOMATIC1111:master' into feat/latent-upscale-modes
|
3 years ago |
|
AUTOMATIC
|
4ec6470a1a
|
fix checkpoint list API
|
3 years ago |
|
MMaker
|
15fd0b8bc4
|
Update processing.py
|
3 years ago |
|
MMaker
|
96cf15bede
|
Add new latent upscale modes
|
3 years ago |
|
AUTOMATIC
|
8d8a05a3bb
|
find configs for models at runtime rather than when starting
|
3 years ago |
|
AUTOMATIC
|
02d7abf514
|
helpful error message when trying to load 2.0 without config
failing to load model weights from settings won't break generation for currently loaded model anymore
|
3 years ago |
|
MMaker
|
e5b7ee910e
|
fix: Save full res of intermediate step
|
3 years ago |
Max Weber
|
917b5bd8d0
|
ui: save dropdown sampling method to the ui-config
|
3 years ago |
|
AUTOMATIC
|
3e22e29413
|
fix broken send to extras button
|
3 years ago |
|
AUTOMATIC
|
82cfc227d7
|
added licenses screen to settings
added footer
removed unused inpainting code
|
3 years ago |
|
Vladimir Mandic
|
d8d206c168
|
add state to interrogate
|
3 years ago |
|
Vladimir Mandic
|
cec209981e
|
log only sdapi
|
3 years ago |
|
AUTOMATIC
|
8f96f92899
|
call script callbacks for reloaded model after loading embeddings
|
3 years ago |
|
AUTOMATIC
|
2d5a5076bb
|
Make it so that upscalers are not repeated when restarting UI.
|
3 years ago |
|
Vladimir Mandic
|
192ddc04d6
|
add job info to modules
|
3 years ago |