de64146ad2
add number of itter
3 years ago
c07f1d0d78
Convert callbacks into a private map, add utility functions for removing callbacks
3 years ago
f1b6ac64e4
Added option to preview Created images on batch completion.
3 years ago
a9e979977a
process_one
3 years ago
e21fcd72fc
add back png info in image api
3 years ago
fb3b564801
Merge branch 'master' into fix-ckpt-cache
3 years ago
7ea5956ad5
now add
3 years ago
10b280e9a2
Merge branch 'AUTOMATIC1111:master' into force-push-patch-13
3 years ago
9b5f85ac83
first revert
3 years ago
3178c35224
resolve conflicts
3 years ago
f2a5cbe6f5
fix #3986 breaking --no-half-vae
3 years ago
675b51ebd3
Merge pull request #3986 from R-N/vae-picker
...
VAE Selector
3 years ago
e359268be9
Merge pull request #3976 from victorca25/esrgan_fea
...
multiple trivial changes for "extras" models
3 years ago
bb21a4cb35
Merge pull request #3715 from shwang95/master
...
Fix error caused by EXIF transpose when using custom scripts
3 years ago
e6060a7e6b
Merge pull request #4155 from MaikoTan/fix/register-api-in-api-only-mode
...
fix: should invoke callback as well in api only mode
3 years ago
eb5e82c7dd
do not unnecessarily run VAE one more time when saving intermediate image with hires fix
3 years ago
9c67408004
Allow saving "before-highres-fix. ( #4150 )
...
* Save image/s before doing highres fix.
3 years ago
4a8cf01f6f
remove duplicate code from #3970
3 years ago
e526f6b378
Merge pull request #3970 from evshiron/fix/progress-api
...
fix broken progress api and current image compatibility
3 years ago
af6fba2475
Merge branch 'master' into master
3 years ago
a5409a6e4b
Save VAE provided by cmd_opts.vae_path
3 years ago
dd2108fdac
fix: should invoke callback as well in api only mode
3 years ago
95c6308ccd
switch to gradio 3.8
3 years ago
5c864be010
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
056f06d373
Reload VAE without reloading sd checkpoint
3 years ago
51e0a83969
Merge branch 'master' into fix/progress-api
3 years ago
65522ff157
Merge pull request #4142 from jn-jairo/processing-close
...
Release processing resources after it finishes
3 years ago
10f62546d3
Merge pull request #4021 from AUTOMATIC1111/add-kdiff-cfgdenoiser-callback
...
Add mid-kdiffusion cfgdenoiser script callback - access latents, conditionings and sigmas mid-sampling
3 years ago
5510c282b1
fix for extensions' javascript not loading
3 years ago
c9148b2312
Release processing resources after it finishes
3 years ago
5b6bedf6f2
Update class name and assign back to vars
3 years ago
cd88e21dc5
Class Name typo and add descriptions to fields.
3 years ago
f8c6468d42
Merge branch 'master' into vae-picker
3 years ago
198a1ffcfc
fix API returning extra stuff in base64 encoded iamges for #3972
3 years ago
d51a5d6336
Merge pull request #4025 from evshiron/feat/interrupt-api-master
...
prototype interrupt api
3 years ago
efd20a4519
Merge pull request #4026 from AUTOMATIC1111/extras-cache-key-extension
...
Extend extras image cache key with upscale_first arg
3 years ago
d7622d97f2
Merge pull request #4004 from mamawr/master
...
Added "--clip-models-path" switch
3 years ago
f071a1d25a
Merge pull request #4056 from MarkovInequality/TI_optimizations
...
Allow TI training using 6GB VRAM when xformers is available
3 years ago
0e5d239f06
Merge pull request #4086 from timntorres/3875-allow-disabling-png-info
...
Add PNG info to pngs only if option is enabled.
3 years ago
467cae167a
append_tag_shuffle
3 years ago
c28de154b0
Merge pull request #4087 from ikasumi/feat/batch-img2img-improve
...
make save dir if save dir is not exists
3 years ago
d79b93084c
Merge pull request #3723 from stysmmaker/patch/image-save-callback
...
Correct before image saved callback
3 years ago
d35bf64945
make launch.py run installers for extensions that have ones
...
add some more classes to safety module for an extension
3 years ago
f126986b76
Merge pull request #4098 from jn-jairo/load-model
...
Unload sd_model before loading the other to solve the issue #3449
3 years ago
0874404040
Merge pull request #3982 from MaikoTan/on-started-callback
...
feat: add app started callback
3 years ago
b88505925b
Merge branch 'AUTOMATIC1111:master' into adjust-ddim-uniform-steps
3 years ago
af758e97fa
Unload sd_model before loading the other
3 years ago
5b0f624bdc
Added Available tab to extensions UI.
3 years ago
525c1edf43
make save dir if save dir is not exists
3 years ago
8792be5007
Add PNG info to pngs only if option is enabled.
3 years ago
3f3d14afd5
nix unused thing
3 years ago
df6a7ebfe8
revert things to master
3 years ago
509fd1459b
Merge remote-tracking branch 'upstream/master' into roy.add_simple_interrogate_api
3 years ago
9e22a35754
fix the error with extension tab not working because of the previous commit
3 years ago
58cc03edd0
fix scripts I broke with the extension tab changes
3 years ago
dc7425a56e
disable access to extension stuff for non-local servers
3 years ago
910a097ae2
add initial version of the extensions tab
...
fix broken Restart Gradio button
3 years ago
890e68aaf7
Fixed minor bug
...
when unloading vae during TI training, generating images after
training will error out
3 years ago
3b0127e698
Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webui into TI_optimizations
3 years ago
006756f9cd
Added TI training optimizations
...
option to use xattention optimizations when training
option to unload vae when training
3 years ago
bf7a699845
Fix #4035 for real now
3 years ago
36966e3200
Fix #4035
3 years ago
726769da35
Checkpoint cache by combination key of checkpoint and vae
3 years ago
b96d0c4e9e
Fix typo from previous commit
3 years ago
29f758afe9
Extend extras image cache with upscale_first arg
3 years ago
adaa699e38
prototype interrupt api
3 years ago
081df45da4
docs: add python doc (?)
...
not sure if this available...
3 years ago
8ae0ea9dea
Add callback to sd_samplers
3 years ago
8906be85ac
add callback cleardown
3 years ago
21fba39c60
Add callbacks and param objects
3 years ago
d9e4e4d7a0
Fix non-square full resolution inpainting.
3 years ago
d587586d3b
Added "--clip-models-path" switch to avoid using default "~/.cache/clip" and enable to run under unprivileged user without homedir
3 years ago
6c9e427c0e
Merge branch 'AUTOMATIC1111:master' into adjust-ddim-uniform-steps
3 years ago
e1b2ea6e00
Change VAE search order and thus priority
3 years ago
cb31abcf58
Settings to select VAE
3 years ago
423f222283
feat: add app started callback
3 years ago
c9bb33dd43
add resrgan 8x, allow use 1x and up to 8x extra models, move BSRGAN model, add nearest
3 years ago
9d96d7d0a0
resolve conflicts
3 years ago
20194fd975
We have duplicate linear now
3 years ago
4b8a192f68
add optimizer save option to shared.opts
3 years ago
34c86c12b0
Include PLMS in adjust steps as it also can fail in the same way
3 years ago
1a4ff2de6a
fix current image in progress api when parallel processing enabled
3 years ago
be27fd4690
fix broken progress api by previous rework
3 years ago
71571e3f05
Replaced master branch fix with updated fix.
3 years ago
15468c9939
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
17a2076f72
Merge pull request #3928 from R-N/validate-before-load
...
Optimize training a little
3 years ago
3dc9a43f7e
Merge pull request #3898 from R-N/lr-comma
...
Allow trailing comma in learning rate
3 years ago
149784202c
rework #3722 to not introduce duplicate code
3 years ago
060ee5d3a7
Merge pull request #3722 from evshiron/feat/progress-api
...
prototype progress api
3 years ago
61836bd544
shorten Hypernetwork strength in infotext and omit it when it's the default value.
3 years ago
470f184176
Merge pull request #3831 from timntorres/3825-save-hypernet-strength-to-info
...
Save Hypernetwork strength to infotext.
3 years ago
05a657dd35
fix broken hires fix
3 years ago
9f4f894d74
allow skip current image in progress api
3 years ago
66d038f6a4
Read hypernet strength from PNG info.
3 years ago
e709afb0f7
Merge commit 'e7254746bbfbff45099db44a8d4d25dd6181877d' into 3825-save-hypernet-strength-to-info
3 years ago
9f104b53c4
preview current image when opts.show_progress_every_n_steps is enabled
3 years ago
39f55c3c35
Re-add explicit device move
3 years ago
88f46a5bec
update progress response model
3 years ago
e9c6c2a51f
add description for state field
3 years ago
f62db4d5c7
fix progress response model
3 years ago
7f5212fb5f
Merge branch 'master' into feat/progress-api
3 years ago
6b719c49b1
Merge branch 'master' into feat/progress-api
3 years ago
c328deb5f1
Merge pull request #3934 from bamarillo/api-add-png-info-endpoint
...
[API][Feature] Add png info endpoint
3 years ago
9bb6b6509a
add postprocess call for scripts
3 years ago
83a1f44ae2
Fix space
3 years ago
4609b83cd4
Add PNG Info endpoint
3 years ago
3d58510f21
Fix dataset still being loaded even when training will be skipped
3 years ago
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
3 years ago
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.
3 years ago
ab05a74ead
Revert "Add cleanup after training"
...
This reverts commit 3ce2bfdf95
3 years ago
44ab954fab
Fix latent upscale highres fix #3888
3 years ago
de1dc0d279
Add adjust_steps_if_invalid to find next valid step for ddim uniform sampler
3 years ago
a27d19de2e
Additional assert on dataset
3 years ago
3ce2bfdf95
Add cleanup after training
3 years ago
ab27c111d0
Add input validations before loading dataset for training
3 years ago
ef4c94e1cf
Improve lr schedule error message
3 years ago
a5f3adbdd7
Allow trailing comma in learning rate
3 years ago
35c45df28b
fix broken ↙ button, fix field paste ignoring most of useful fields for for #3768
3 years ago
2c4d203884
Revert "Explicitly state when Hypernet is none."
3 years ago
e98f72be33
Merge branch 'AUTOMATIC1111:master' into 3825-save-hypernet-strength-to-info
3 years ago
beb6fc2979
move send seed option to UI section and make it false by default
3 years ago
9553a7e071
Merge pull request #3818 from jwatzman/master
...
Reduce peak memory usage when changing models
3 years ago
28e6d4a54e
add element ids for save buttons for #3798
3 years ago
76086f6668
Merge branch 'master' into modal-save-button-and-shortcut
3 years ago
f3454b8a6b
Merge pull request #3691 from xmodar/arabic
...
Revamped Arabic localization
3 years ago
2922d8144f
make existing image browser extension not break
3 years ago
af547f63c3
Merge branch 'Inspiron'
3 years ago
3c207ca684
add needed imports fr new code in copypaste.py
3 years ago
a33d0a9a65
remove weird spaces added to ui.py over time
3 years ago
2d220afb24
fix open folder button not working
3 years ago
a1e5e0d766
skip filenames starting with . for img2img and extras batch modes
3 years ago
cf8da8e1b0
Merge pull request #3826 from ANTONIOPSD/patch-1
...
Natural sorting for dropdown checkpoint list
3 years ago
810e6a407d
Merge pull request #3858 from R-N/log-csv
...
Fix log off by 1 #3847
3 years ago
3019452927
Merge pull request #3803 from FlameLaw/master
...
Fixed proper dataset shuffling
3 years ago
86e19fe873
Merge pull request #3669 from random-thoughtss/master
...
Added option to use unmasked conditioning image for inpainting model.
3 years ago
1fba573d24
Merge pull request #3874 from cobryan05/extra_tweak
...
Extras Tab - Option to upscale before face fix, caching improvements
3 years ago
bce5adcd6d
change default hypernet activation function to linear
3 years ago
f3685281e2
Merge pull request #3877 from Yaiol/master
...
Filename tags are wrongly referencing to process size instead of image size
3 years ago
d3b4b9d7ec
Merge pull request #3717 from benkyoujouzu/master
...
Add missing support for linear activation in hypernetwork
3 years ago
fc89495df3
Merge pull request #3771 from aria1th/patch-12
...
Disable unavailable or duplicate options for Activation functions
3 years ago
0edf100d83
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
f361e804eb
Re enable linear
3 years ago
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.
3 years ago
d8b3661467
extras: upscaler blending should not be considered in cache key
3 years ago
5732c0282d
extras-tweaks: autoformat changed lines
3 years ago
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.
3 years ago
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.
3 years ago
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.
3 years ago
9ceef81f77
Fix log off by 1
3 years ago
db5a354c48
Always ignore "None.pt" in the hypernet directory.
3 years ago
c0677b3316
Explicitly state when Hypernet is none.
3 years ago
d4a069a23c
Read hypernet strength from PNG info.
3 years ago
9e465c8aa5
Add strength to textinfo.
3 years ago
b2a8b263b2
Add missing support for linear activation in hypernetwork
3 years ago
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
3 years ago
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.
3 years ago
bdc9083798
Add a barebones interrogate API
3 years ago
b68c7c437e
Updated name and hover text.
3 years ago
a38496c1de
Moved mask weight config to SD section
3 years ago
26a3fd2fe9
Highres fix works with unmasked latent.
...
Also refactor the mask creation to make it more accesible.
3 years ago
f3f2ffd448
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
a0a7024c67
Fix random dataset shuffle on TI
3 years ago
268159cfe3
fixed indentation
3 years ago
0995e879ce
added save button and shortcut (s) to Modal View
3 years ago
e0cbf53f45
create send to buttons by extensions
3 years ago
462e6ba667
Disable unavailable or duplicate options
3 years ago
029d7c7543
Revert unresolved changes in Bias initialization
...
it should be zeros_ or parameterized in future properly.
3 years ago
cc56df996e
Fix dropout logic
3 years ago
85fcccc105
Squashed commit of fixing dropout silently
...
fix dropouts for future hypernetworks
add kwargs for Hypernetwork class
hypernet UI for gradio input
add recommended options
remove as options
revert adding options in ui
3 years ago
4a4647e0df
create send to buttons in one module
3 years ago
3de0365141
Add id access to scripts list in the css
3 years ago
0dd8480281
fix: Correct before image saved callback
3 years ago
fddb4883f4
prototype progress api
3 years ago
737eb28fac
typo: cmd_opts.embedding_dir to cmd_opts.embeddings_dir
3 years ago
b2e0d8ba78
Remove folder endpoint
3 years ago
8320963dcb
Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webui
3 years ago
7bd8581e46
Fix error caused by EXIF transpose when using custom scripts
...
Some custom scripts read image directly and no need to select image in UI, this will cause error.
3 years ago
0cd7460253
add script callback for before image save and change callback for after image save to use a class with parameters
3 years ago
1e428238db
add override_settings to API as an alternative to #3629
3 years ago
b6a8bb123b
Fix merge
3 years ago
f4e1464217
Implement PR #3625 but for embeddings.
3 years ago
4875a6c217
Implement PR #3309 but for embeddings.
3 years ago
c2dc9bfa89
Implement PR #3189 but for embeddings.
3 years ago
a524d137d0
patch bug (SeverianVoid's comment on 5245c7a)
3 years ago
cb49800c08
img2img, use smartphone photos' EXIF orientation
3 years ago
91bb35b1e6
Merge fix
3 years ago
649d79a8ec
Merge branch 'master' into hn-activation
3 years ago
9d82c351ac
fix typo in on_save_imaged/on_image_saved; hope no extension is using it yet
3 years ago
757264c453
default_time_format if format is blank
3 years ago
877d94f97c
Back compatibility
3 years ago
146856f66d
images: allow nested bracket in filename pattern
3 years ago
b46c64c6e5
clean
3 years ago
db9ab1a46b
[Bugfix][API] - Fix API response for colab users
3 years ago
cbb857b675
enable creating embedding with --medvram
3 years ago
ee73341f04
Merge pull request #3139 from captin411/focal-point-cropping
...
[Preprocess image] New option to auto crop based on complexity, edges, faces
3 years ago
7207e3bf49
remove duplicate keys and lowercase
3 years ago
de096d0ce7
Weight initialization and More activation func
...
add weight init
add weight init option in create_hypernetwork
fstringify hypernet info
save weight initialization info for further debugging
fill bias with zero for He/Xavier
initialize LayerNorm with Normal
fix loading weight_init
3 years ago
c702d4d0df
Fix off-by-one
3 years ago
2f4c91894d
Remove activation from final layer of HNs
3 years ago
df0c5ea29d
update default weights
3 years ago
Artem Zagidulin
DepFA
Kyu♥
evshiron
Muhammad Rizqi Nur
AngelBottomless
AUTOMATIC
timntorres
KyuSeok Jung
Maiko Tan
Sihan Wang
Jairo Correa
TinkTheBoush
Martin Cairns
k_sugawara
timntorres
Roy Shilkrot
Fampai
random_thoughtss
mawr
victorca25
random-thoughtss
Bruno Seoane
Bruno Seoane
Yaiol
Chris OBryan
benkyoujouzu
Antonio
Josh Watzman
FlameLaw
Florian Horn
yfszzx
guaneec
xmodar
MMaker
w-e-w
Milly
Stephen
captin411