brkirch
|
5deb2a19cc
|
Allow Doggettx's cross attention opt without CUDA
|
2023-01-06 01:33:15 -05:00 |
|
brkirch
|
b95a4c0ce5
|
Change sub-quad chunk threshold to use percentage
|
2023-01-06 01:01:51 -05:00 |
|
AUTOMATIC
|
683287d87f
|
rework saving training params to file #6372
|
2023-01-06 08:52:06 +03:00 |
|
brkirch
|
b119815333
|
Use narrow instead of dynamic_slice
|
2023-01-06 00:15:24 -05:00 |
|
brkirch
|
3bfe2bb549
|
Merge remote-tracking branch 'upstream/master' into sub-quad_attn_opt
|
2023-01-06 00:15:22 -05:00 |
|
brkirch
|
f6ab5a39d7
|
Merge branch 'AUTOMATIC1111:master' into sub-quad_attn_opt
|
2023-01-06 00:14:20 -05:00 |
|
brkirch
|
d782a95967
|
Add Birch-san's sub-quadratic attention implementation
|
2023-01-06 00:14:13 -05:00 |
|
AUTOMATIC1111
|
88e01b237e
|
Merge pull request #6372 from timntorres/save-ti-hypernet-settings-to-txt-revised
Save hypernet and textual inversion settings to text file, revised.
|
2023-01-06 07:59:44 +03:00 |
|
AUTOMATIC1111
|
143ed5a42d
|
Merge pull request #6384 from faber6/loads-ti-from-subdirs
allow loading embeddings from subdirectories
|
2023-01-06 07:56:48 +03:00 |
|
AUTOMATIC1111
|
8a13afd216
|
Merge pull request #6401 from acncagua/wsl-open
wsl-open
|
2023-01-06 07:56:15 +03:00 |
|
AUTOMATIC1111
|
85fa4eacea
|
Merge pull request #6402 from brkirch/work-with-nightly-local-builds
Add support for using PyTorch nightly and local builds
|
2023-01-06 07:51:45 +03:00 |
|
AUTOMATIC1111
|
3ea354f274
|
Merge pull request #6364 from 0xb8/master
hires-fix: add "nearest-exact" latent upscale mode.
|
2023-01-06 07:49:11 +03:00 |
|
acncagua
|
d61a5aa4f6
|
Add files via upload
|
2023-01-06 10:58:22 +09:00 |
|
brkirch
|
8111b5569d
|
Add support for PyTorch nightly and local builds
|
2023-01-05 20:54:52 -05:00 |
|
noodleanon
|
b5253f0dab
|
allow img2img api to run scripts
|
2023-01-05 21:21:48 +00:00 |
|
Faber
|
81133d4168
|
allow loading embeddings from subdirectories
|
2023-01-06 03:38:37 +07:00 |
|
AUTOMATIC1111
|
310b71f669
|
Merge pull request #6376 from KumiIT/master
typo in TI
|
2023-01-05 22:10:07 +03:00 |
|
AUTOMATIC
|
847f869c67
|
experimental optimization
|
2023-01-05 21:00:52 +03:00 |
|
Kuma
|
fda04e620d
|
typo in TI
|
2023-01-05 18:44:19 +01:00 |
|
timntorres
|
b6bab2f052
|
Include model in log file. Exclude directory.
|
2023-01-05 09:14:56 -08:00 |
|
timntorres
|
b85c2b5cf4
|
Clean up ti, add same behavior to hypernetwork.
|
2023-01-05 08:14:38 -08:00 |
|
cat
|
19a81ac287
|
hires-fix: add "nearest-exact" latent upscale mode.
|
2023-01-05 20:25:02 +05:00 |
|
timntorres
|
eea8fc40e1
|
Add option to save ti settings to file.
|
2023-01-05 07:24:22 -08:00 |
|
AUTOMATIC
|
f8d0cf6a6e
|
rework #6329 to remove duplicate code and add prevent tab names for showing in ids for scripts that only exist on one tab
|
2023-01-05 12:08:11 +03:00 |
|
AUTOMATIC
|
997461d3dd
|
add footer with versions
|
2023-01-05 11:57:14 +03:00 |
|
AUTOMATIC1111
|
01a1fee874
|
Merge pull request #6329 from Kryptortio/add_even_more_element_ids
Add additional elem_id/HTML ids (again)
|
2023-01-05 11:56:13 +03:00 |
|
AUTOMATIC
|
42fcc79bd3
|
add Discard penultimate sigma to infotext
|
2023-01-05 10:43:21 +03:00 |
|
AUTOMATIC1111
|
c53852e257
|
Merge pull request #6044 from hentailord85ez/discard-penultimate-sigma
Allow always discarding of penultimate sigma and fix doing 1 less step than specified
|
2023-01-05 10:33:51 +03:00 |
|
AUTOMATIC1111
|
24e21c0710
|
Merge pull request #6328 from lolsuffocate/fix-png-info-api
Make pnginfoapi return all image info
|
2023-01-05 10:23:59 +03:00 |
|
AUTOMATIC
|
2e30997450
|
move sd_model assignment to the place where we change the sd_model
|
2023-01-05 10:21:17 +03:00 |
|
Philpax
|
83ca8dd0c9
|
Merge branch 'AUTOMATIC1111:master' into fix-sd-arch-switch-in-override-settings
|
2023-01-05 05:00:58 +01:00 |
|
AUTOMATIC
|
99b67cff0b
|
make hires fix not do anything if the user chooses the second pass resolution to be the same as first pass resolution
|
2023-01-05 01:25:52 +03:00 |
|
me
|
5851bc839b
|
Add element ids for script components and a few more in ui.py
|
2023-01-04 22:14:30 +01:00 |
|
AUTOMATIC
|
bc43293c64
|
fix incorrect display/calculation for number of steps for hires fix in progress bars
|
2023-01-04 23:56:43 +03:00 |
|
Suffocate
|
1288a3bb7d
|
Use the read_info_from_image function directly
|
2023-01-04 20:36:30 +00:00 |
|
AUTOMATIC
|
8149078094
|
added the option to specify target resolution with possibility of truncating for hires fix; also sampling steps
|
2023-01-04 22:04:40 +03:00 |
|
AUTOMATIC
|
24d4a0841d
|
train tab visual updates
allow setting train tab values from ui-config.json
|
2023-01-04 20:10:40 +03:00 |
|
AUTOMATIC1111
|
eeb1de4388
|
Merge branch 'master' into gradient-clipping
|
2023-01-04 19:56:35 +03:00 |
|
AUTOMATIC1111
|
e9911391ca
|
Merge pull request #6305 from vladmandic/fix-jpeg
fix jpeg handling
|
2023-01-04 19:22:51 +03:00 |
|
AUTOMATIC
|
097a90b88b
|
add XY plot parameters to grid image and do not add them to individual images
|
2023-01-04 19:19:11 +03:00 |
|
AUTOMATIC
|
3dae545a03
|
rename weirdly named variables from #3176
|
2023-01-04 18:42:51 +03:00 |
|
AUTOMATIC1111
|
37aafdb059
|
Merge branch 'master' into master
|
2023-01-04 18:39:57 +03:00 |
|
AUTOMATIC
|
a8eb9e3bf8
|
Revert "Merge pull request #3791 from shirayu/fix/filename"
This reverts commit eed58279e7, reversing
changes made to 4ae960b01c.
|
2023-01-04 18:20:38 +03:00 |
|
AUTOMATIC1111
|
eed58279e7
|
Merge pull request #3791 from shirayu/fix/filename
Truncate too long filename (Fix #705)
|
2023-01-04 18:17:50 +03:00 |
|
AUTOMATIC
|
525cea9245
|
use shared function from processing for creating dummy mask when training inpainting model
|
2023-01-04 17:58:07 +03:00 |
|
Vladimir Mandic
|
590c5ae016
|
update pillow
|
2023-01-04 09:48:54 -05:00 |
|
AUTOMATIC
|
184e670126
|
fix the merge
|
2023-01-04 17:45:01 +03:00 |
|
AUTOMATIC1111
|
da5c1e8a73
|
Merge branch 'master' into inpaint_textual_inversion
|
2023-01-04 17:40:19 +03:00 |
|
AUTOMATIC1111
|
47df084901
|
Merge pull request #6304 from vladmandic/add-cross-attention-info
add cross-attention info
|
2023-01-04 17:30:43 +03:00 |
|
AUTOMATIC
|
4d66bf2c0d
|
add infotext to "-before-highres-fix" images
|
2023-01-04 17:24:46 +03:00 |
|
Vladimir Mandic
|
79c682ad4f
|
fix jpeg
|
2023-01-04 08:20:42 -05:00 |
|
AUTOMATIC
|
1cfd8aec4a
|
make it possible to work with opts.show_progress_every_n_steps = -1 with medvram
|
2023-01-04 16:05:42 +03:00 |
|
Vladimir Mandic
|
21ee77db31
|
add cross-attention info
|
2023-01-04 08:04:38 -05:00 |
|
AUTOMATIC1111
|
c923de0e05
|
Merge pull request #5969 from philpax/include-job-timestamp-in-progress-api
feat(api): include job_timestamp in progress
|
2023-01-04 15:28:51 +03:00 |
|
AUTOMATIC
|
642142556d
|
use commandline-supplied cuda device name instead of cuda:0 for safetensors PR that doesn't fix anything
|
2023-01-04 15:09:53 +03:00 |
|
AUTOMATIC
|
68fbf4558f
|
Merge remote-tracking branch 'Narsil/fix_safetensors_load_speed'
|
2023-01-04 14:53:03 +03:00 |
|
Vladimir Mandic
|
11b8160a08
|
fix typo
|
2023-01-04 06:36:57 -05:00 |
|
AUTOMATIC
|
0cd6399b8b
|
fix broken inpainting model
|
2023-01-04 14:29:13 +03:00 |
|
AUTOMATIC
|
3bd737767b
|
disable broken API logging
|
2023-01-04 14:20:32 +03:00 |
|
AUTOMATIC1111
|
7bbd984dda
|
Merge pull request #6253 from Shondoit/ti-optim
Save Optimizer next to TI embedding
|
2023-01-04 14:09:13 +03:00 |
|
AUTOMATIC1111
|
545ae8cb1c
|
Merge pull request #6264 from vladmandic/add-state-info
add missing state info
|
2023-01-04 14:04:50 +03:00 |
|
AUTOMATIC1111
|
a8ad8666cd
|
Merge pull request #6261 from vladmandic/api-logging
add api logging
|
2023-01-04 14:04:11 +03:00 |
|
AUTOMATIC1111
|
6281c1bdb4
|
Merge pull request #6299 from stysmmaker/feat/latent-upscale-modes
Add more latent upscale modes
|
2023-01-04 13:47:36 +03:00 |
|
AUTOMATIC1111
|
77c3bc7747
|
Merge pull request #6298 from stysmmaker/fix/intermediate-step-full-res
Save full resolution of intermediate step
|
2023-01-04 13:46:21 +03:00 |
|
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
|
2023-01-04 05:36:18 -05:00 |
|
MMaker
|
f49f917cdd
|
Merge branch 'AUTOMATIC1111:master' into feat/latent-upscale-modes
|
2023-01-04 04:27:52 -06:00 |
|
AUTOMATIC
|
4ec6470a1a
|
fix checkpoint list API
|
2023-01-04 13:26:23 +03:00 |
|
MMaker
|
15fd0b8bc4
|
Update processing.py
|
2023-01-04 05:12:54 -05:00 |
|
MMaker
|
96cf15bede
|
Add new latent upscale modes
|
2023-01-04 05:12:06 -05:00 |
|
AUTOMATIC
|
8d8a05a3bb
|
find configs for models at runtime rather than when starting
|
2023-01-04 12:47:42 +03:00 |
|
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
|
2023-01-04 12:35:07 +03:00 |
|
MMaker
|
e5b7ee910e
|
fix: Save full res of intermediate step
|
2023-01-04 04:22:01 -05:00 |
|
Max Weber
|
917b5bd8d0
|
ui: save dropdown sampling method to the ui-config
|
2023-01-03 18:19:56 -07:00 |
|
AUTOMATIC
|
3e22e29413
|
fix broken send to extras button
|
2023-01-03 21:49:24 +03:00 |
|
AUTOMATIC
|
82cfc227d7
|
added licenses screen to settings
added footer
removed unused inpainting code
|
2023-01-03 20:23:17 +03:00 |
|
Vladimir Mandic
|
d8d206c168
|
add state to interrogate
|
2023-01-03 11:01:04 -05:00 |
|
Vladimir Mandic
|
cec209981e
|
log only sdapi
|
2023-01-03 10:58:52 -05:00 |
|
AUTOMATIC
|
8f96f92899
|
call script callbacks for reloaded model after loading embeddings
|
2023-01-03 18:39:14 +03:00 |
|
AUTOMATIC
|
2d5a5076bb
|
Make it so that upscalers are not repeated when restarting UI.
|
2023-01-03 18:38:21 +03:00 |
|
Vladimir Mandic
|
192ddc04d6
|
add job info to modules
|
2023-01-03 10:34:51 -05:00 |
|
Vladimir Mandic
|
1d9dc48efd
|
init job and add info to model merge
|
2023-01-03 10:21:51 -05:00 |
|
Vladimir Mandic
|
aaa4c2aacb
|
add api logging
|
2023-01-03 09:45:16 -05:00 |
|
AUTOMATIC
|
e9fb9bb0c2
|
fix hires fix not working in API when user does not specify upscaler
|
2023-01-03 17:40:20 +03:00 |
|
Shondoit
|
bddebe09ed
|
Save Optimizer next to TI embedding
Also add check to load only .PT and .BIN files as embeddings. (since we add .optim files in the same directory)
|
2023-01-03 13:30:24 +01:00 |
|
AUTOMATIC
|
c0ee148870
|
add support for running with gradio 3.9 installed
|
2023-01-03 14:18:48 +03:00 |
|
AUTOMATIC
|
a1cf55a9d1
|
add option to reorder items in main UI
|
2023-01-03 10:39:21 +03:00 |
|
AUTOMATIC
|
9d4eff097d
|
add a button to show all setting pages
|
2023-01-03 10:01:06 +03:00 |
|
AUTOMATIC
|
2bc86712ec
|
make quicksettings UI elements appear in same order as they are listed in the setting
|
2023-01-03 09:13:35 +03:00 |
|
AUTOMATIC
|
18c03cdeac
|
styling rework to make things more compact
|
2023-01-03 09:04:29 +03:00 |
|
AUTOMATIC
|
269f6e8676
|
change settings UI to use vertical tabs
|
2023-01-03 07:20:20 +03:00 |
|
AUTOMATIC
|
251ecee694
|
make "send to" buttons send actual dimension of the sent image rather than fields
|
2023-01-02 22:44:46 +03:00 |
|
AUTOMATIC
|
8d12a729b8
|
fix possible error with accessing nonexistent setting
|
2023-01-02 20:46:51 +03:00 |
|
AUTOMATIC
|
84dd7e8e24
|
error out with a readable message in chwewckpoint merger for incompatible tensor shapes (ie when trying to merge SD1.5 with SD2.0)
|
2023-01-02 20:30:02 +03:00 |
|
AUTOMATIC
|
4dbde228ff
|
make it possible to use fractional values for SD upscale.
|
2023-01-02 20:01:16 +03:00 |
|
AUTOMATIC
|
ef27a18b6b
|
Hires fix rework
|
2023-01-02 19:42:10 +03:00 |
|
AUTOMATIC1111
|
fd4461d44c
|
Merge pull request #6196 from philpax/add-embeddings-api
feat(api): add /sdapi/v1/embeddings
|
2023-01-02 06:11:10 +03:00 |
|
AUTOMATIC1111
|
f39a79d143
|
Merge pull request #6183 from Kryptortio/add_more_element_ids
Add additional elem_id/HTML ids
|
2023-01-02 06:10:26 +03:00 |
|
Philpax
|
c65909ad16
|
feat(api): return more data for embeddings
|
2023-01-02 12:21:48 +11:00 |
|
Philpax
|
b5819d9bf1
|
feat(api): add /sdapi/v1/embeddings
|
2023-01-02 10:18:11 +11:00 |
|
AUTOMATIC
|
311354c0bb
|
fix the issue with training on SD2.0
|
2023-01-02 00:38:09 +03:00 |
|