AUTOMATIC1111
3019452927
Merge pull request #3803 from FlameLaw/master
...
Fixed proper dataset shuffling
3 years ago
AUTOMATIC1111
86e19fe873
Merge pull request #3669 from random-thoughtss/master
...
Added option to use unmasked conditioning image for inpainting model.
3 years ago
AUTOMATIC1111
1fba573d24
Merge pull request #3874 from cobryan05/extra_tweak
...
Extras Tab - Option to upscale before face fix, caching improvements
3 years ago
AUTOMATIC
bce5adcd6d
change default hypernet activation function to linear
3 years ago
AUTOMATIC1111
f3685281e2
Merge pull request #3877 from Yaiol/master
...
Filename tags are wrongly referencing to process size instead of image size
3 years ago
AUTOMATIC1111
d3b4b9d7ec
Merge pull request #3717 from benkyoujouzu/master
...
Add missing support for linear activation in hypernetwork
3 years ago
AUTOMATIC1111
fc89495df3
Merge pull request #3771 from aria1th/patch-12
...
Disable unavailable or duplicate options for Activation functions
3 years ago
Bruno Seoane
0edf100d83
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
AngelBottomless
f361e804eb
Re enable linear
3 years ago
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.
3 years ago
Chris OBryan
d8b3661467
extras: upscaler blending should not be considered in cache key
3 years ago
Chris OBryan
5732c0282d
extras-tweaks: autoformat changed lines
3 years ago
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.
3 years ago
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.
3 years ago
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.
3 years ago
Muhammad Rizqi Nur
9ceef81f77
Fix log off by 1
3 years ago
timntorres
db5a354c48
Always ignore "None.pt" in the hypernet directory.
3 years ago
timntorres
c0677b3316
Explicitly state when Hypernet is none.
3 years ago
timntorres
d4a069a23c
Read hypernet strength from PNG info.
3 years ago
timntorres
9e465c8aa5
Add strength to textinfo.
3 years ago
benkyoujouzu
b2a8b263b2
Add missing support for linear activation in hypernetwork
3 years ago
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
3 years ago
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.
3 years ago
random_thoughtss
b68c7c437e
Updated name and hover text.
3 years ago
random_thoughtss
a38496c1de
Moved mask weight config to SD section
3 years ago
random_thoughtss
26a3fd2fe9
Highres fix works with unmasked latent.
...
Also refactor the mask creation to make it more accesible.
3 years ago
random-thoughtss
f3f2ffd448
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
FlameLaw
a0a7024c67
Fix random dataset shuffle on TI
3 years ago
Florian Horn
268159cfe3
fixed indentation
3 years ago
Florian Horn
0995e879ce
added save button and shortcut (s) to Modal View
3 years ago
yfszzx
e0cbf53f45
create send to buttons by extensions
3 years ago
AngelBottomless
462e6ba667
Disable unavailable or duplicate options
3 years ago
yfszzx
4a4647e0df
create send to buttons in one module
3 years ago
xmodar
3de0365141
Add id access to scripts list in the css
3 years ago
evshiron
fddb4883f4
prototype progress api
3 years ago
DepFA
737eb28fac
typo: cmd_opts.embedding_dir to cmd_opts.embeddings_dir
3 years ago
Bruno Seoane
b2e0d8ba78
Remove folder endpoint
3 years ago
Bruno Seoane
8320963dcb
Merge branch 'master' of https://github.com/AUTOMATIC1111/stable-diffusion-webui
3 years ago
AUTOMATIC
0cd7460253
add script callback for before image save and change callback for after image save to use a class with parameters
3 years ago
AUTOMATIC
1e428238db
add override_settings to API as an alternative to #3629
3 years ago
timntorres
f4e1464217
Implement PR #3625 but for embeddings.
3 years ago
timntorres
4875a6c217
Implement PR #3309 but for embeddings.
3 years ago
timntorres
c2dc9bfa89
Implement PR #3189 but for embeddings.
3 years ago
timntorres
a524d137d0
patch bug (SeverianVoid's comment on 5245c7a)
3 years ago
timntorres
cb49800c08
img2img, use smartphone photos' EXIF orientation
3 years ago
AUTOMATIC
9d82c351ac
fix typo in on_save_imaged/on_image_saved; hope no extension is using it yet
3 years ago
w-e-w
757264c453
default_time_format if format is blank
3 years ago
Milly
146856f66d
images: allow nested bracket in filename pattern
3 years ago
Stephen
b46c64c6e5
clean
3 years ago
Stephen
db9ab1a46b
[Bugfix][API] - Fix API response for colab users
3 years ago
AUTOMATIC
cbb857b675
enable creating embedding with --medvram
3 years ago
AUTOMATIC1111
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
AngelBottomless
7207e3bf49
remove duplicate keys and lowercase
3 years ago
AngelBottomless
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
captin411
df0c5ea29d
update default weights
3 years ago
captin411
54f0c14824
download better face detection module dynamically
3 years ago
captin411
db8ed5fe5c
Focal crop UI elements
3 years ago
captin411
6629446a2f
Merge branch 'master' into focal-point-cropping
3 years ago
random_thoughtss
8b4f32779f
Switch to a continous blend for cond. image.
3 years ago
captin411
3e6c2420c1
improve debug markers, fix algo weighting
3 years ago
random_thoughtss
605d27687f
Added conditioning image masking to xy_grid.
...
Use `True` and `False` to select values.
3 years ago
random_thoughtss
f9549d1cbb
Added option to use unmasked conditioning image.
3 years ago
不会画画的中医不是好程序员
4ff4730d82
Merge branch 'AUTOMATIC1111:master' into Inspiron
3 years ago
yfszzx
f300d0f2b4
Merge branch 'Inspiron' of https://github.com/yfszzx/stable-diffusion-webui-plus into Inspiron
3 years ago
yfszzx
9ba439b533
need some rights for extensions
3 years ago
AUTOMATIC
3e15f8e0f5
update callbacks code for #3549
3 years ago
不会画画的中医不是好程序员
5bfa2b23ca
Merge branch 'AUTOMATIC1111:master' into Inspiron
3 years ago
yfszzx
ff305acd51
some rights for extensions
3 years ago
w-e-w
91c1e1e6a9
fix default filename pattern
3 years ago
brkirch
faed465a0b
MPS Upscalers Fix
...
Get ESRGAN, SCUNet, and SwinIR working correctly on MPS by ensuring memory is contiguous for tensor views before sending to MPS device.
3 years ago
brkirch
4c24347e45
Remove BSRGAN from --use-cpu, add SwinIR
3 years ago
AUTOMATIC1111
16416e42b5
Merge branch 'master' into on-image-saved-callback
3 years ago
AUTOMATIC
77a320f406
do not stop execution when script's callback misbehaves and report which script it was
3 years ago
ritosonn
b383702752
fix #3145 #3093
3 years ago
w-e-w
0c0028a9d3
UnknownTimeZoneError
3 years ago
yfszzx
cb9d2f8705
move to img component to public
3 years ago
Bruno Seoane
2267498a8c
Merge remote-tracking branch 'upstream/master'
3 years ago
Bruno Seoane
595dca85af
Reverse run_extras change
...
Update serialization on the batch images endpoint
3 years ago
AUTOMATIC
2c05e06ea7
rename api/processing to api/models for #3511
3 years ago
AUTOMATIC
8da1bd48bf
add an option to skip adding number to filenames when saving.
...
rework filename pattern function go through the pattern once and not calculate any of replacements until they are actually encountered in the pattern.
3 years ago
yfszzx
994aaadf08
a strange bug
3 years ago
w-e-w
eb007e5884
use the same datetime object for [date] and [datetime]
3 years ago
w-e-w
5a981310e6
replace_datetime() can now accept a datetime parameter
3 years ago
w-e-w
8f6af4ed65
remove lowercasing file_decoration as it is not needed anymore
3 years ago
w-e-w
00952fb4a8
add sanitize_filename() to datetime
3 years ago
w-e-w
480d8e7646
replace "srt.replace()" in apply_filename_pattern() with equivalent re.sub()
...
the file_decoration passed into apply_filename_pattern() is formatted to lowercase to increase compatibility
the use of case sensitive srt.replace()
but because the newly implemented "time format" is case sensitive
the lowercasing the file_decoration will cause time format to be broken
in order to resolve this issue
I decided to replace every srt.replace() and in if "str" in x to regular expression (case insensitive) equivalent
3 years ago
w-e-w
37dd6deafb
filename pattern [datetime], extended customizable Format and Time Zone
...
format:
[datetime]
[datetime<Format>]
[datetime<Format><Time Zone>]
3 years ago
w-e-w
7d4a4db9ea
modify unnecessary sting assignment as it's going to get overwritten
3 years ago
w-e-w
c5d90628a4
move "file_decoration" initialize section
...
into "if forced_filename is None:"
no need to initialize it if it's not going to be used
3 years ago
w-e-w
3be6b29d81
indent=4 config.json
3 years ago
AUTOMATIC
876a96f0f9
remove erroneous dir in the extension directory
...
remove loading .js files from scripts dir (they go into javascript)
load scripts after models, for scripts that depend on loaded models
3 years ago
AUTOMATIC1111
999929bea4
Merge pull request #3537 from yfszzx/Inspiron
...
Move out images browser from project
3 years ago
Trung Ngo
734986dde3
add callback after image is saved
3 years ago
AUTOMATIC
6cbb04f7a5
fix #3517 breaking txt2img
3 years ago
不会画画的中医不是好程序员
68931242cf
Merge branch 'AUTOMATIC1111:master' into Inspiron
3 years ago
AngelBottomless
e9a410b535
check length for variance
3 years ago
AngelBottomless
0d2e1dac40
convert deque -> list
...
I don't feel this being efficient
3 years ago
AngelBottomless
348f89c8d4
statistics for pbar
3 years ago
AngelBottomless
40b56c9289
cleanup some code
3 years ago
AngelBottomless
b297cc3324
Hypernetworks - fix KeyError in statistics caching
...
Statistics logging has changed to {filename : list[losses]}, so it has to use loss_info[key].pop()
3 years ago