AUTOMATIC
f2a5cbe6f5
fix #3986 breaking --no-half-vae
2022-11-02 14:41:29 +03:00
AUTOMATIC1111
675b51ebd3
Merge pull request #3986 from R-N/vae-picker
...
VAE Selector
2022-11-02 14:12:27 +03:00
AUTOMATIC1111
e359268be9
Merge pull request #3976 from victorca25/esrgan_fea
...
multiple trivial changes for "extras" models
2022-11-02 14:09:38 +03:00
AUTOMATIC1111
bb21a4cb35
Merge pull request #3715 from shwang95/master
...
Fix error caused by EXIF transpose when using custom scripts
2022-11-02 13:41:35 +03:00
AUTOMATIC1111
e6060a7e6b
Merge pull request #4155 from MaikoTan/fix/register-api-in-api-only-mode
...
fix: should invoke callback as well in api only mode
2022-11-02 13:04:55 +03:00
AUTOMATIC
eb5e82c7dd
do not unnecessarily run VAE one more time when saving intermediate image with hires fix
2022-11-02 12:45:03 +03:00
timntorres
9c67408004
Allow saving "before-highres-fix. ( #4150 )
...
* Save image/s before doing highres fix.
2022-11-02 12:18:21 +03:00
AUTOMATIC
4a8cf01f6f
remove duplicate code from #3970
2022-11-02 12:12:32 +03:00
AUTOMATIC1111
e526f6b378
Merge pull request #3970 from evshiron/fix/progress-api
...
fix broken progress api and current image compatibility
2022-11-02 12:06:12 +03:00
KyuSeok Jung
af6fba2475
Merge branch 'master' into master
2022-11-02 17:10:56 +09:00
Muhammad Rizqi Nur
a5409a6e4b
Save VAE provided by cmd_opts.vae_path
2022-11-02 14:37:22 +07:00
Maiko Tan
dd2108fdac
fix: should invoke callback as well in api only mode
2022-11-02 15:04:35 +08:00
AUTOMATIC
95c6308ccd
switch to gradio 3.8
2022-11-02 09:48:02 +03:00
Sihan Wang
5c864be010
Merge branch 'AUTOMATIC1111:master' into master
2022-11-02 14:09:33 +08:00
Muhammad Rizqi Nur
056f06d373
Reload VAE without reloading sd checkpoint
2022-11-02 12:51:46 +07:00
evshiron
51e0a83969
Merge branch 'master' into fix/progress-api
2022-11-02 12:31:33 +08:00
AUTOMATIC1111
65522ff157
Merge pull request #4142 from jn-jairo/processing-close
...
Release processing resources after it finishes
2022-11-02 07:30:03 +03:00
AUTOMATIC1111
10f62546d3
Merge pull request #4021 from AUTOMATIC1111/add-kdiff-cfgdenoiser-callback
...
Add mid-kdiffusion cfgdenoiser script callback - access latents, conditionings and sigmas mid-sampling
2022-11-02 07:29:16 +03:00
AUTOMATIC
5510c282b1
fix for extensions' javascript not loading
2022-11-02 07:26:31 +03:00
Jairo Correa
c9148b2312
Release processing resources after it finishes
2022-11-01 21:56:47 -03:00
DepFA
5b6bedf6f2
Update class name and assign back to vars
2022-11-02 00:38:17 +00:00
DepFA
cd88e21dc5
Class Name typo and add descriptions to fields.
2022-11-02 00:34:58 +00:00
Muhammad Rizqi Nur
f8c6468d42
Merge branch 'master' into vae-picker
2022-11-02 00:25:08 +07:00
AUTOMATIC
198a1ffcfc
fix API returning extra stuff in base64 encoded iamges for #3972
2022-11-01 19:14:10 +03:00
AUTOMATIC1111
d51a5d6336
Merge pull request #4025 from evshiron/feat/interrupt-api-master
...
prototype interrupt api
2022-11-01 18:22:16 +03:00
AUTOMATIC1111
efd20a4519
Merge pull request #4026 from AUTOMATIC1111/extras-cache-key-extension
...
Extend extras image cache key with upscale_first arg
2022-11-01 18:21:54 +03:00
AUTOMATIC1111
d7622d97f2
Merge pull request #4004 from mamawr/master
...
Added "--clip-models-path" switch
2022-11-01 18:19:12 +03:00
AUTOMATIC1111
f071a1d25a
Merge pull request #4056 from MarkovInequality/TI_optimizations
...
Allow TI training using 6GB VRAM when xformers is available
2022-11-01 18:17:56 +03:00
AUTOMATIC1111
0e5d239f06
Merge pull request #4086 from timntorres/3875-allow-disabling-png-info
...
Add PNG info to pngs only if option is enabled.
2022-11-01 18:06:11 +03:00
TinkTheBoush
467cae167a
append_tag_shuffle
2022-11-01 23:29:12 +09:00
AUTOMATIC1111
c28de154b0
Merge pull request #4087 from ikasumi/feat/batch-img2img-improve
...
make save dir if save dir is not exists
2022-11-01 15:08:27 +03:00
AUTOMATIC1111
d79b93084c
Merge pull request #3723 from stysmmaker/patch/image-save-callback
...
Correct before image saved callback
2022-11-01 14:59:10 +03:00
AUTOMATIC
d35bf64945
make launch.py run installers for extensions that have ones
...
add some more classes to safety module for an extension
2022-11-01 14:20:15 +03:00
AUTOMATIC1111
f126986b76
Merge pull request #4098 from jn-jairo/load-model
...
Unload sd_model before loading the other to solve the issue #3449
2022-11-01 13:54:00 +03:00
AUTOMATIC1111
0874404040
Merge pull request #3982 from MaikoTan/on-started-callback
...
feat: add app started callback
2022-11-01 13:47:47 +03:00
Martin Cairns
b88505925b
Merge branch 'AUTOMATIC1111:master' into adjust-ddim-uniform-steps
2022-11-01 08:34:39 +00:00
Jairo Correa
af758e97fa
Unload sd_model before loading the other
2022-11-01 04:01:49 -03:00
AUTOMATIC
5b0f624bdc
Added Available tab to extensions UI.
2022-11-01 09:59:10 +03:00
k_sugawara
525c1edf43
make save dir if save dir is not exists
2022-11-01 09:40:54 +09:00
timntorres
8792be5007
Add PNG info to pngs only if option is enabled.
2022-10-31 17:29:04 -07:00
Roy Shilkrot
3f3d14afd5
nix unused thing
2022-10-31 11:51:21 -04:00
Roy Shilkrot
df6a7ebfe8
revert things to master
2022-10-31 11:50:33 -04:00
Roy Shilkrot
509fd1459b
Merge remote-tracking branch 'upstream/master' into roy.add_simple_interrogate_api
2022-10-31 11:45:52 -04:00
AUTOMATIC
9e22a35754
fix the error with extension tab not working because of the previous commit
2022-10-31 18:45:50 +03:00
AUTOMATIC
58cc03edd0
fix scripts I broke with the extension tab changes
2022-10-31 18:40:47 +03:00
AUTOMATIC
dc7425a56e
disable access to extension stuff for non-local servers
2022-10-31 18:33:44 +03:00
AUTOMATIC
910a097ae2
add initial version of the extensions tab
...
fix broken Restart Gradio button
2022-10-31 17:37:02 +03:00
Fampai
890e68aaf7
Fixed minor bug
...
when unloading vae during TI training, generating images after
training will error out
2022-10-31 10:07:12 -04:00
Fampai
3b0127e698
Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webui into TI_optimizations
2022-10-31 09:54:51 -04:00
Fampai
006756f9cd
Added TI training optimizations
...
option to use xattention optimizations when training
option to unload vae when training
2022-10-31 07:26:08 -04:00
Muhammad Rizqi Nur
bf7a699845
Fix #4035 for real now
2022-10-31 16:27:27 +07:00
Muhammad Rizqi Nur
36966e3200
Fix #4035
2022-10-31 15:38:58 +07:00
Muhammad Rizqi Nur
726769da35
Checkpoint cache by combination key of checkpoint and vae
2022-10-31 15:22:03 +07:00
Muhammad Rizqi Nur
b96d0c4e9e
Fix typo from previous commit
2022-10-31 14:42:28 +07:00
DepFA
29f758afe9
Extend extras image cache with upscale_first arg
2022-10-31 02:39:55 +00:00
evshiron
adaa699e38
prototype interrupt api
2022-10-31 10:31:06 +08:00
Maiko Sinkyaet Tan
081df45da4
docs: add python doc (?)
...
not sure if this available...
2022-10-31 08:47:43 +08:00
DepFA
8ae0ea9dea
Add callback to sd_samplers
2022-10-30 23:48:33 +00:00
DepFA
8906be85ac
add callback cleardown
2022-10-30 23:47:08 +00:00
DepFA
21fba39c60
Add callbacks and param objects
2022-10-30 23:45:52 +00:00
random_thoughtss
d9e4e4d7a0
Fix non-square full resolution inpainting.
2022-10-30 15:33:02 -07:00
mawr
d587586d3b
Added "--clip-models-path" switch to avoid using default "~/.cache/clip" and enable to run under unprivileged user without homedir
2022-10-31 00:14:07 +03:00
Martin Cairns
6c9e427c0e
Merge branch 'AUTOMATIC1111:master' into adjust-ddim-uniform-steps
2022-10-30 17:03:25 +00:00
Muhammad Rizqi Nur
e1b2ea6e00
Change VAE search order and thus priority
2022-10-30 22:11:45 +07:00
Muhammad Rizqi Nur
cb31abcf58
Settings to select VAE
2022-10-30 21:54:31 +07:00
Maiko Tan
423f222283
feat: add app started callback
2022-10-30 22:46:43 +08:00
victorca25
c9bb33dd43
add resrgan 8x, allow use 1x and up to 8x extra models, move BSRGAN model, add nearest
2022-10-30 12:54:06 +01:00
aria1th
9d96d7d0a0
resolve conflicts
2022-10-30 20:40:59 +09:00
AngelBottomless
20194fd975
We have duplicate linear now
2022-10-30 20:40:59 +09:00
AngelBottomless
4b8a192f68
add optimizer save option to shared.opts
2022-10-30 20:40:59 +09:00
Martin Cairns
34c86c12b0
Include PLMS in adjust steps as it also can fail in the same way
2022-10-30 11:04:27 +00:00
evshiron
1a4ff2de6a
fix current image in progress api when parallel processing enabled
2022-10-30 17:02:47 +08:00
evshiron
be27fd4690
fix broken progress api by previous rework
2022-10-30 17:01:10 +08:00
random_thoughtss
71571e3f05
Replaced master branch fix with updated fix.
2022-10-30 00:35:40 -07:00
random-thoughtss
15468c9939
Merge branch 'AUTOMATIC1111:master' into master
2022-10-30 00:30:18 -07:00
AUTOMATIC1111
17a2076f72
Merge pull request #3928 from R-N/validate-before-load
...
Optimize training a little
2022-10-30 09:51:36 +03:00
AUTOMATIC1111
3dc9a43f7e
Merge pull request #3898 from R-N/lr-comma
...
Allow trailing comma in learning rate
2022-10-30 09:29:29 +03:00
AUTOMATIC
149784202c
rework #3722 to not introduce duplicate code
2022-10-30 09:10:22 +03:00
AUTOMATIC1111
060ee5d3a7
Merge pull request #3722 from evshiron/feat/progress-api
...
prototype progress api
2022-10-30 09:02:01 +03:00
AUTOMATIC
61836bd544
shorten Hypernetwork strength in infotext and omit it when it's the default value.
2022-10-30 08:48:53 +03:00
AUTOMATIC1111
470f184176
Merge pull request #3831 from timntorres/3825-save-hypernet-strength-to-info
...
Save Hypernetwork strength to infotext.
2022-10-30 08:47:18 +03:00
AUTOMATIC
05a657dd35
fix broken hires fix
2022-10-30 07:41:56 +03:00
evshiron
9f4f894d74
allow skip current image in progress api
2022-10-30 06:03:32 +08:00
timntorres
66d038f6a4
Read hypernet strength from PNG info.
2022-10-29 15:00:08 -07:00
timntorres
e709afb0f7
Merge commit 'e7254746bbfbff45099db44a8d4d25dd6181877d' into 3825-save-hypernet-strength-to-info
2022-10-29 14:55:30 -07:00
evshiron
9f104b53c4
preview current image when opts.show_progress_every_n_steps is enabled
2022-10-30 05:19:17 +08:00
random_thoughtss
39f55c3c35
Re-add explicit device move
2022-10-29 14:13:02 -07:00
evshiron
88f46a5bec
update progress response model
2022-10-30 05:04:29 +08:00
evshiron
e9c6c2a51f
add description for state field
2022-10-30 04:02:56 +08:00
evshiron
f62db4d5c7
fix progress response model
2022-10-30 03:56:44 +08:00
evshiron
7f5212fb5f
Merge branch 'master' into feat/progress-api
2022-10-30 03:49:00 +08:00
evshiron
6b719c49b1
Merge branch 'master' into feat/progress-api
2022-10-30 03:45:29 +08:00
AUTOMATIC1111
c328deb5f1
Merge pull request #3934 from bamarillo/api-add-png-info-endpoint
...
[API][Feature] Add png info endpoint
2022-10-29 22:20:50 +03:00
AUTOMATIC
9bb6b6509a
add postprocess call for scripts
2022-10-29 22:20:02 +03:00
Bruno Seoane
83a1f44ae2
Fix space
2022-10-29 16:10:00 -03:00
Bruno Seoane
4609b83cd4
Add PNG Info endpoint
2022-10-29 16:09:19 -03:00
Muhammad Rizqi Nur
3d58510f21
Fix dataset still being loaded even when training will be skipped
2022-10-30 00:54:59 +07:00
Muhammad Rizqi Nur
a07f054c86
Add missing info on hypernetwork/embedding model log
...
Mentioned here: https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/1528#discussioncomment-3991513
Also group the saving into one
2022-10-30 00:49:29 +07:00
random_thoughtss
6e2ce4e735
Added image conditioning to latent upscale.
...
Only comuted if the mask weight is not 1.0 to avoid extra memory.
Also includes some code cleanup.
2022-10-29 10:35:51 -07:00
Muhammad Rizqi Nur
ab05a74ead
Revert "Add cleanup after training"
...
This reverts commit 3ce2bfdf95
2022-10-30 00:32:02 +07:00
random_thoughtss
44ab954fab
Fix latent upscale highres fix #3888
2022-10-29 10:02:56 -07:00
Martin Cairns
de1dc0d279
Add adjust_steps_if_invalid to find next valid step for ddim uniform sampler
2022-10-29 15:23:19 +01:00
Muhammad Rizqi Nur
a27d19de2e
Additional assert on dataset
2022-10-29 19:44:05 +07:00
Muhammad Rizqi Nur
3ce2bfdf95
Add cleanup after training
2022-10-29 19:43:21 +07:00
Muhammad Rizqi Nur
ab27c111d0
Add input validations before loading dataset for training
2022-10-29 18:09:17 +07:00
Muhammad Rizqi Nur
ef4c94e1cf
Improve lr schedule error message
2022-10-29 15:42:51 +07:00
Muhammad Rizqi Nur
a5f3adbdd7
Allow trailing comma in learning rate
2022-10-29 15:37:24 +07:00
AUTOMATIC
35c45df28b
fix broken ↙ button, fix field paste ignoring most of useful fields for for #3768
2022-10-29 10:56:19 +03:00
timntorres
2c4d203884
Revert "Explicitly state when Hypernet is none."
2022-10-29 00:36:51 -07:00
timntorres
e98f72be33
Merge branch 'AUTOMATIC1111:master' into 3825-save-hypernet-strength-to-info
2022-10-29 00:31:23 -07:00
AUTOMATIC
beb6fc2979
move send seed option to UI section and make it false by default
2022-10-29 09:57:22 +03:00
AUTOMATIC1111
9553a7e071
Merge pull request #3818 from jwatzman/master
...
Reduce peak memory usage when changing models
2022-10-29 09:16:00 +03:00
AUTOMATIC
28e6d4a54e
add element ids for save buttons for #3798
2022-10-29 09:13:36 +03:00
AUTOMATIC1111
76086f6668
Merge branch 'master' into modal-save-button-and-shortcut
2022-10-29 09:11:00 +03:00
AUTOMATIC1111
f3454b8a6b
Merge pull request #3691 from xmodar/arabic
...
Revamped Arabic localization
2022-10-29 09:03:35 +03:00
AUTOMATIC
2922d8144f
make existing image browser extension not break
2022-10-29 09:01:04 +03:00
AUTOMATIC
af547f63c3
Merge branch 'Inspiron'
2022-10-29 08:48:11 +03:00
AUTOMATIC
3c207ca684
add needed imports fr new code in copypaste.py
2022-10-29 08:42:34 +03:00
AUTOMATIC
a33d0a9a65
remove weird spaces added to ui.py over time
2022-10-29 08:28:48 +03:00
AUTOMATIC
2d220afb24
fix open folder button not working
2022-10-29 08:26:12 +03:00
AUTOMATIC
a1e5e0d766
skip filenames starting with . for img2img and extras batch modes
2022-10-29 08:11:03 +03:00
AUTOMATIC1111
cf8da8e1b0
Merge pull request #3826 from ANTONIOPSD/patch-1
...
Natural sorting for dropdown checkpoint list
2022-10-29 08:02:03 +03:00
AUTOMATIC1111
810e6a407d
Merge pull request #3858 from R-N/log-csv
...
Fix log off by 1 #3847
2022-10-29 07:55:20 +03:00
AUTOMATIC1111
3019452927
Merge pull request #3803 from FlameLaw/master
...
Fixed proper dataset shuffling
2022-10-29 07:52:51 +03:00
AUTOMATIC1111
86e19fe873
Merge pull request #3669 from random-thoughtss/master
...
Added option to use unmasked conditioning image for inpainting model.
2022-10-29 07:49:48 +03:00
AUTOMATIC1111
1fba573d24
Merge pull request #3874 from cobryan05/extra_tweak
...
Extras Tab - Option to upscale before face fix, caching improvements
2022-10-29 07:44:17 +03:00
AUTOMATIC
bce5adcd6d
change default hypernet activation function to linear
2022-10-29 07:37:06 +03:00
AUTOMATIC1111
f3685281e2
Merge pull request #3877 from Yaiol/master
...
Filename tags are wrongly referencing to process size instead of image size
2022-10-29 07:32:11 +03:00
AUTOMATIC1111
d3b4b9d7ec
Merge pull request #3717 from benkyoujouzu/master
...
Add missing support for linear activation in hypernetwork
2022-10-29 07:30:14 +03:00
AUTOMATIC1111
fc89495df3
Merge pull request #3771 from aria1th/patch-12
...
Disable unavailable or duplicate options for Activation functions
2022-10-29 07:29:02 +03:00
Bruno Seoane
0edf100d83
Merge branch 'AUTOMATIC1111:master' into master
2022-10-28 22:03:49 -03:00
AngelBottomless
f361e804eb
Re enable linear
2022-10-29 08:36:50 +09:00
Yaiol
539c0f51e4
Update images.py
...
Filename tags [height] and [width] are wrongly referencing to process size instead of resulting image size. Making all upscale files named wrongly.
2022-10-29 01:07:01 +02:00
Chris OBryan
d8b3661467
extras: upscaler blending should not be considered in cache key
2022-10-28 16:55:02 -05:00
Chris OBryan
5732c0282d
extras-tweaks: autoformat changed lines
2022-10-28 16:36:25 -05:00
Chris OBryan
1f1b327959
extras: Make image cache LRU
...
This changes the extras image cache into a Least-Recently-Used
cache. This allows more experimentation with different upscalers
without missing the cache.
Max cache size is increased to 5 and is cleared on source image
update.
2022-10-28 16:14:21 -05:00
Chris OBryan
bde4731f1d
extras: Rework image cache
...
Bit of a refactor to the image cache to make it easier to extend.
Also takes into account the entire image instead of just a cropped portion.
2022-10-28 14:44:25 -05:00
Chris OBryan
26d0819384
extras: Add option to run upscaling before face fixing
...
Face restoration can look much better if ran after upscaling, as it
allows the restoration to fix upscaling artifacts. This patch adds
an option to choose which order to run upscaling/face fixing in.
2022-10-28 13:33:49 -05:00
Muhammad Rizqi Nur
9ceef81f77
Fix log off by 1
2022-10-28 20:48:08 +07:00
timntorres
db5a354c48
Always ignore "None.pt" in the hypernet directory.
2022-10-28 01:41:57 -07:00
timntorres
c0677b3316
Explicitly state when Hypernet is none.
2022-10-27 23:31:45 -07:00
timntorres
d4a069a23c
Read hypernet strength from PNG info.
2022-10-27 23:16:27 -07:00
timntorres
9e465c8aa5
Add strength to textinfo.
2022-10-27 23:03:34 -07:00
benkyoujouzu
b2a8b263b2
Add missing support for linear activation in hypernetwork
2022-10-28 12:54:59 +08:00
Antonio
5d5dc64064
Natural sorting for dropdown checkpoint list
...
Example:
Before After
11.ckpt 11.ckpt
ab.ckpt ab.ckpt
ade_pablo_step_1000.ckpt ade_pablo_step_500.ckpt
ade_pablo_step_500.ckpt ade_pablo_step_1000.ckpt
ade_step_1000.ckpt ade_step_500.ckpt
ade_step_1500.ckpt ade_step_1000.ckpt
ade_step_2000.ckpt ade_step_1500.ckpt
ade_step_2500.ckpt ade_step_2000.ckpt
ade_step_3000.ckpt ade_step_2500.ckpt
ade_step_500.ckpt ade_step_3000.ckpt
atp_step_5500.ckpt atp_step_5500.ckpt
model1.ckpt model1.ckpt
model10.ckpt model10.ckpt
model1000.ckpt model33.ckpt
model33.ckpt model50.ckpt
model400.ckpt model400.ckpt
model50.ckpt model1000.ckpt
moo44.ckpt moo44.ckpt
v1-4-pruned-emaonly.ckpt v1-4-pruned-emaonly.ckpt
v1-5-pruned-emaonly.ckpt v1-5-pruned-emaonly.ckpt
v1-5-pruned.ckpt v1-5-pruned.ckpt
v1-5-vae.ckpt v1-5-vae.ckpt
2022-10-28 05:49:39 +02:00
Josh Watzman
b50ff4f4e4
Reduce peak memory usage when changing models
...
A few tweaks to reduce peak memory usage, the biggest being that if we
aren't using the checkpoint cache, we shouldn't duplicate the model
state dict just to immediately throw it away.
On my machine with 16GB of RAM, this change means I can typically change
models, whereas before it would typically OOM.
2022-10-27 22:01:06 +01:00
Roy Shilkrot
bdc9083798
Add a barebones interrogate API
2022-10-27 15:20:15 -04:00
random_thoughtss
b68c7c437e
Updated name and hover text.
2022-10-27 11:45:35 -07:00
random_thoughtss
a38496c1de
Moved mask weight config to SD section
2022-10-27 11:31:31 -07:00
random_thoughtss
26a3fd2fe9
Highres fix works with unmasked latent.
...
Also refactor the mask creation to make it more accesible.
2022-10-27 11:27:59 -07:00
