7207e3bf49
remove duplicate keys and lowercase
2022-10-26 09:17:01 +03:00
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
2022-10-26 09:17:01 +03:00
df0c5ea29d
update default weights
2022-10-25 17:06:59 -07:00
54f0c14824
download better face detection module dynamically
2022-10-25 16:14:13 -07:00
db8ed5fe5c
Focal crop UI elements
2022-10-25 15:22:29 -07:00
6629446a2f
Merge branch 'master' into focal-point-cropping
2022-10-25 13:22:27 -07:00
8b4f32779f
Switch to a continous blend for cond. image.
2022-10-25 13:15:08 -07:00
3e6c2420c1
improve debug markers, fix algo weighting
2022-10-25 13:13:12 -07:00
605d27687f
Added conditioning image masking to xy_grid.
...
Use `True` and `False` to select values.
2022-10-25 12:20:54 -07:00
f9549d1cbb
Added option to use unmasked conditioning image.
2022-10-25 11:14:12 -07:00
4ff4730d82
Merge branch 'AUTOMATIC1111:master' into Inspiron
2022-10-25 19:09:38 +08:00
f300d0f2b4
Merge branch 'Inspiron' of https://github.com/yfszzx/stable-diffusion-webui-plus into Inspiron
2022-10-25 18:48:24 +08:00
9ba439b533
need some rights for extensions
2022-10-25 18:48:07 +08:00
3e15f8e0f5
update callbacks code for #3549
2022-10-25 12:16:25 +03:00
5bfa2b23ca
Merge branch 'AUTOMATIC1111:master' into Inspiron
2022-10-25 15:38:33 +08:00
ff305acd51
some rights for extensions
2022-10-25 15:33:43 +08:00
91c1e1e6a9
fix default filename pattern
2022-10-25 09:44:54 +03:00
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.
2022-10-25 09:42:53 +03:00
4c24347e45
Remove BSRGAN from --use-cpu, add SwinIR
2022-10-25 09:42:53 +03:00
16416e42b5
Merge branch 'master' into on-image-saved-callback
2022-10-25 08:40:12 +03:00
77a320f406
do not stop execution when script's callback misbehaves and report which script it was
2022-10-25 08:32:47 +03:00
b383702752
fix #3145 #3093
2022-10-25 08:32:33 +03:00
0c0028a9d3
UnknownTimeZoneError
2022-10-24 16:01:48 +03:00
cb9d2f8705
move to img component to public
2022-10-24 20:06:53 +08:00
2267498a8c
Merge remote-tracking branch 'upstream/master'
2022-10-24 08:37:37 -03:00
595dca85af
Reverse run_extras change
...
Update serialization on the batch images endpoint
2022-10-24 08:32:18 -03:00
2c05e06ea7
rename api/processing to api/models for #3511
2022-10-24 14:11:14 +03:00
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.
2022-10-24 14:03:58 +03:00
994aaadf08
a strange bug
2022-10-24 16:44:36 +08:00
eb007e5884
use the same datetime object for [date] and [datetime]
2022-10-24 10:28:42 +03:00
5a981310e6
replace_datetime() can now accept a datetime parameter
2022-10-24 10:28:42 +03:00
8f6af4ed65
remove lowercasing file_decoration as it is not needed anymore
2022-10-24 10:28:42 +03:00
00952fb4a8
add sanitize_filename() to datetime
2022-10-24 10:28:42 +03:00
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
2022-10-24 10:28:42 +03:00
37dd6deafb
filename pattern [datetime], extended customizable Format and Time Zone
...
format:
[datetime]
[datetime<Format>]
[datetime<Format><Time Zone>]
2022-10-24 10:28:42 +03:00
7d4a4db9ea
modify unnecessary sting assignment as it's going to get overwritten
2022-10-24 10:28:42 +03:00
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
2022-10-24 10:28:42 +03:00
3be6b29d81
indent=4 config.json
2022-10-24 10:22:48 +03:00
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
2022-10-24 09:39:46 +03:00
999929bea4
Merge pull request #3537 from yfszzx/Inspiron
...
Move out images browser from project
2022-10-24 09:28:37 +03:00
734986dde3
add callback after image is saved
2022-10-24 01:25:31 -05:00
6cbb04f7a5
fix #3517 breaking txt2img
2022-10-24 09:15:26 +03:00
68931242cf
Merge branch 'AUTOMATIC1111:master' into Inspiron
2022-10-24 14:09:27 +08:00
e9a410b535
check length for variance
2022-10-24 09:07:39 +03:00
0d2e1dac40
convert deque -> list
...
I don't feel this being efficient
2022-10-24 09:07:39 +03:00
348f89c8d4
statistics for pbar
2022-10-24 09:07:39 +03:00
40b56c9289
cleanup some code
2022-10-24 09:07:39 +03:00
b297cc3324
Hypernetworks - fix KeyError in statistics caching
...
Statistics logging has changed to {filename : list[losses]}, so it has to use loss_info[key].pop()
2022-10-24 09:07:39 +03:00
f2cc3f32d5
fix whitespaces
2022-10-24 08:58:56 +03:00
9741969325
Save properly processed image before color correction
2022-10-24 08:58:56 +03:00
a889c93f23
paste_fields add to public
2022-10-24 11:13:16 +08:00
cef1b89aa2
remove browser to extension
2022-10-24 10:10:33 +08:00
124e44cf1e
remove browser to extension
2022-10-24 09:51:56 +08:00
90f02c7522
Remove unused field and class
2022-10-23 16:05:54 -03:00
1e625624ba
Add folder processing endpoint
...
Also minor refactor
2022-10-23 16:01:16 -03:00
866b36d705
Move processing's models into models.py
...
It didn't make sense to have two differente files for the same and
"models" is a more descriptive name.
2022-10-23 15:35:49 -03:00
e0ca4dfbc1
Update endpoints to use gradio's own utils functions
2022-10-23 15:13:37 -03:00
e3f0e34cd6
Merge branch 'master' of https://github.com/bamarillo/stable-diffusion-webui
2022-10-23 13:14:54 -03:00
4ff852ffb5
Add batch processing "extras" endpoint
2022-10-23 13:07:59 -03:00
0523704dad
Update run_extras to use the temp filename
...
In batch mode run_extras tries to preserve the original file name of the
images. The problem is that this makes no sense since the user only gets
a list of images in the UI, trying to manually save them shows that this
images have random temp names. Also, trying to keep "orig_name" in the
API is a hassle that adds complexity to the consuming UI since the
client has to use (or emulate) an input (type=file) element in a form.
Using the normal file name not only doesn't change the output and
functionality in the original UI but also helps keep the API simple.
2022-10-23 12:27:50 -03:00
1be5933ba2
auto cropping now works with non square crops
2022-10-23 04:11:07 -07:00
6bd6154a92
Merge pull request #2067 from victorca25/esrgan_mod
...
update ESRGAN architecture and model to support all ESRGAN models
2022-10-23 13:43:41 +03:00
6a9ea40d7f
Move browser and Inspiration into extension
2022-10-23 16:17:37 +08:00
5dc0739ecd
working mask
2022-10-23 09:26:56 +03:00
9e1a8b7734
non-implemented mask with any type
2022-10-23 09:26:56 +03:00
a7c213d0f5
[API][Feature] - Add img2img API endpoint
2022-10-23 09:26:56 +03:00
1fbfc052eb
Update hypernetwork.py
2022-10-23 08:34:33 +03:00
28e26c2bef
Add "extra" single image operation
...
- Separate extra modes into 3 endpoints so the user ddoesn't ahve to
handle so many unused parameters.
- Add response model for codumentation
2022-10-22 23:17:27 -03:00
b02926df13
Moved moodels to their own file and extracted base64 conversion to its own function
2022-10-22 20:24:04 -03:00
1b4d04737a
Remove unused imports
2022-10-22 20:13:16 -03:00
48dbf99e84
Allow tracking real-time loss
...
Someone had 6000 images in their dataset, and it was shown as 0, which was confusing.
This will allow tracking real time dataset-average loss for registered objects.
2022-10-22 22:24:19 +03:00
ca5a9e79dc
fix for img2img color correction in a batch #3218
2022-10-22 22:06:54 +03:00
be748e8b08
add --freeze-settings commandline argument to disable changing settings
2022-10-22 22:05:22 +03:00
d213d6ca6f
removed the option to use 2x more memory when generating previews
...
added an option to always only show one image in previews
removed duplicate code
2022-10-22 20:48:13 +03:00
4fdb53c1e9
Generate grid preview for progress image
2022-10-22 20:36:04 +03:00
24694e5983
Update hypernetwork.py
2022-10-22 20:25:32 +03:00
321bacc6a9
call model_loaded_callback after setting shared.sd_model in case scripts refer to it using that
2022-10-22 20:15:12 +03:00
0df94d3fcf
fix aesthetic gradients doing nothing after loading a different model
2022-10-22 20:14:18 +03:00
324c7c732d
record First pass size as 0x0 for #3328
2022-10-22 20:09:51 +03:00
ffea9b1509
Merge pull request #3414 from discus0434/master
...
[Hypernetworks] Add a feature to use dropout / more activation functions
2022-10-22 19:32:13 +03:00
e38625011c
fix part2
2022-10-22 19:27:16 +03:00
72383abacd
Deepdanbooru linux fix
2022-10-22 19:27:16 +03:00
dbc8ab65f6
typo
2022-10-22 19:19:17 +03:00
d37cfffd53
added callback for creating new settings in extensions
2022-10-22 19:18:56 +03:00
6a4fa73a38
small fix
2022-10-22 13:44:39 +00:00
97749b7c7d
Merge branch 'AUTOMATIC1111:master' into master
2022-10-22 22:00:59 +09:00
7912acef72
small fix
2022-10-22 13:00:44 +00:00
fccba4729d
add an option to avoid dying relu
2022-10-22 12:02:41 +00:00
7fd90128eb
added a guard for hypernet training that will stop early if weights are getting no gradients
2022-10-22 14:48:43 +03:00
1cd3ed7def
fix for extensions without style.css
2022-10-22 14:28:56 +03:00
dcb45dfecf
Merge branch 'master' of upstream
2022-10-22 11:14:46 +00:00
0e8ca8e7af
add dropout
2022-10-22 11:07:00 +00:00
50b5504401
remove parsing command line from devices.py
2022-10-22 14:04:14 +03:00
1fa53dab2c
Merge branch 'master' into cuda-device-id-selection
2022-10-22 13:57:20 +03:00
6398dc9b10
further support for extensions
2022-10-22 13:34:49 +03:00
2b91251637
removed aesthetic gradients as built-in
...
added support for extensions
2022-10-22 12:23:58 +03:00
67b78f0ea6
inspiration perfected
2022-10-22 10:29:23 +08:00
d93ea5cdeb
inspiration perfected
2022-10-22 10:21:21 +08:00
40ddb6df61
inspiration perfected
2022-10-22 10:16:22 +08:00
29bfacd63c
implement CUDA device selection, --device-id arg
2022-10-22 00:12:46 +02:00
57eb54b838
implement CUDA device selection by ID
2022-10-22 00:11:07 +02:00
bb0f1a2cda
inspiration finished
2022-10-22 01:23:00 +08:00
26d1073745
Merge remote-tracking branch 'historytab/master'
2022-10-21 18:49:56 +03:00
f49c08ea56
prevent error spam when processing images without txt files for captions
2022-10-21 18:46:02 +03:00
5e9afa5c8a
Merge branch 'master' into fix/train-preprocess-keep-ratio
2022-10-21 18:36:29 +03:00
ac0aa2b18e
loading SD VAE, see PR #3303
2022-10-21 17:35:51 +03:00
704036ff07
make aspect ratio overlay work regardless of selected localization
2022-10-21 17:11:42 +03:00
02e4d4694d
Change option description of unload_models_when_training
2022-10-21 16:53:06 +03:00
272fa527bb
Remove unused variable.
2022-10-21 16:52:24 +03:00
fccad18a59
Refer to Hypernet's name, sensibly, by its name variable.
2022-10-21 16:52:24 +03:00
19818f023c
Match hypernet name with filename in all cases.
2022-10-21 16:52:24 +03:00
51e3dc9cca
Sanitize hypernet name input.
2022-10-21 16:52:24 +03:00
306e2ff6ab
Update image_embedding.py
2022-10-21 16:47:37 +03:00
d0ea471b0c
Use opts in textual_inversion image_embedding.py for dynamic fonts
2022-10-21 16:47:37 +03:00
9286fe53de
make aestetic embedding ciompatible with prompts longer than 75 tokens
2022-10-21 16:38:06 +03:00
df57064093
do not load aesthetic clip model until it's needed
...
add refresh button for aesthetic embeddings
add aesthetic params to images' infotext
2022-10-21 16:10:51 +03:00
7d6b388d71
Merge branch 'ae'
2022-10-21 13:35:01 +03:00
bf30673f51
Fix Hypernet infotext string split bug for PR #3283
2022-10-21 10:19:25 +03:00
03a1e288c4
turns out LayerNorm also has weight and bias and needs to be pre-multiplied and trained for hypernets
2022-10-21 10:13:24 +03:00
0c5522ea21
Merge branch 'master' into training-help-text
2022-10-21 09:57:55 +03:00
2273e752fb
Remove redundant try/except.
2022-10-21 09:55:00 +03:00
4ff274e1e3
Revise comments.
2022-10-21 09:55:00 +03:00
6014fb8afb
Do nothing if image file already exists.
2022-10-21 09:55:00 +03:00
5245c7a493
Issue #2921-Give PNG info to Hypernet previews.
2022-10-21 09:55:00 +03:00
b69c37d25e
Allow datasets with only 1 image in TI
2022-10-21 09:54:09 +03:00
7157e5d064
interrogate: Fix CLIP-interrogation on CPU
...
Currently, trying to perform CLIP interrogation on a CPU fails, saying:
```
RuntimeError: "slow_conv2d_cpu" not implemented for 'Half'
```
This merge request fixes this issue by detecting whether the target
device is CPU and, if so, force-enabling `--no-half` and passing
`device="cpu"` to `clip.load()` (which then does some extra tricks to
ensure it works correctly on CPU).
2022-10-21 09:52:12 +03:00
d6bd6a425d
Merge branch 'master' into master
2022-10-21 09:49:32 +03:00
c23f666dba
a more strict check for activation type and a more reasonable check for type of layer in hypernets
2022-10-21 09:47:43 +03:00
a26fc2834c
Merge pull request #3199 from discus0434/master
...
Add features to insert activation functions to hypernetworks
2022-10-21 09:34:45 +03:00
9d71eef02e
sort file list in alphabetical ordering in extras
2022-10-21 09:00:46 +03:00
a13c3bed3c
Fixed path issue while extras batch processing
2022-10-21 09:00:46 +03:00
fb5a8cf0d9
Added try except to extras batch from directory
2022-10-21 09:00:45 +03:00
60872c5b40
Fixed path issue while extras batch processing
2022-10-21 09:00:45 +03:00
74088c2a06
allow float sizes for hypernet's layer_structure
2022-10-21 09:00:45 +03:00
4587218190
updated readme and some small stylistic changes to code
2022-10-21 09:00:39 +03:00
49533eed9e
XY grid correctly re-assignes model when config changes
2022-10-20 16:01:27 -07:00
d23a46ceaa
Different approach to skip/interrupt with highres fix
2022-10-20 23:49:14 +03:00
708c3a7bd8
Added PLMS hijack and made sure to always replace methods
2022-10-20 13:28:43 -07:00
d1cb08bfb2
fix skip and interrupt for highres. fix option
2022-10-20 22:49:06 +03:00
92a17a7a4a
Made dummy latents smaller. Minor code cleanups
2022-10-20 09:45:03 -07:00
f89829ec3a
Revert "fix bugs and optimizations"
...
This reverts commit 108be15500
2022-10-21 01:37:11 +09:00
dc66540629
Merge branch 'AUTOMATIC1111:master' into Inspiron
2022-10-21 00:07:31 +08:00
108be15500
fix bugs and optimizations
2022-10-21 01:00:41 +09:00
d07cb46f34
inspiration pull request
2022-10-20 23:58:52 +08:00
a71e021236
only linear
2022-10-20 23:48:52 +09:00
d8acd34f66
generalized some functions and option for ignoring first layer
2022-10-20 23:43:03 +09:00
85dd62c4c7
train: ui: added `Split image threshold` and `Split image overlap ratio` to preprocess
2022-10-20 23:35:01 +09:00
9681419e42
train: fixed preprocess image ratio
2022-10-20 23:32:41 +09:00
f8733ad08b
add linear as a act func (option for doin nothing)
2022-10-20 11:07:37 +00:00
6b38c2c19c
Merge branch 'AUTOMATIC1111:master' into master
2022-10-20 18:51:12 +09:00
AngelBottomless