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
54f0c14824
download better face detection module dynamically
3 years ago
db8ed5fe5c
Focal crop UI elements
3 years ago
6629446a2f
Merge branch 'master' into focal-point-cropping
3 years ago
8b4f32779f
Switch to a continous blend for cond. image.
3 years ago
3e6c2420c1
improve debug markers, fix algo weighting
3 years ago
605d27687f
Added conditioning image masking to xy_grid.
...
Use `True` and `False` to select values.
3 years ago
f9549d1cbb
Added option to use unmasked conditioning image.
3 years ago
4ff4730d82
Merge branch 'AUTOMATIC1111:master' into Inspiron
3 years ago
f300d0f2b4
Merge branch 'Inspiron' of https://github.com/yfszzx/stable-diffusion-webui-plus into Inspiron
3 years ago
9ba439b533
need some rights for extensions
3 years ago
3e15f8e0f5
update callbacks code for #3549
3 years ago
5bfa2b23ca
Merge branch 'AUTOMATIC1111:master' into Inspiron
3 years ago
ff305acd51
some rights for extensions
3 years ago
91c1e1e6a9
fix default filename pattern
3 years ago
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
4c24347e45
Remove BSRGAN from --use-cpu, add SwinIR
3 years ago
16416e42b5
Merge branch 'master' into on-image-saved-callback
3 years ago
77a320f406
do not stop execution when script's callback misbehaves and report which script it was
3 years ago
b383702752
fix #3145 #3093
3 years ago
0c0028a9d3
UnknownTimeZoneError
3 years ago
cb9d2f8705
move to img component to public
3 years ago
2267498a8c
Merge remote-tracking branch 'upstream/master'
3 years ago
595dca85af
Reverse run_extras change
...
Update serialization on the batch images endpoint
3 years ago
2c05e06ea7
rename api/processing to api/models for #3511
3 years ago
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
994aaadf08
a strange bug
3 years ago
eb007e5884
use the same datetime object for [date] and [datetime]
3 years ago
5a981310e6
replace_datetime() can now accept a datetime parameter
3 years ago
8f6af4ed65
remove lowercasing file_decoration as it is not needed anymore
3 years ago
00952fb4a8
add sanitize_filename() to datetime
3 years ago
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
37dd6deafb
filename pattern [datetime], extended customizable Format and Time Zone
...
format:
[datetime]
[datetime<Format>]
[datetime<Format><Time Zone>]
3 years ago
7d4a4db9ea
modify unnecessary sting assignment as it's going to get overwritten
3 years ago
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
3be6b29d81
indent=4 config.json
3 years ago
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
999929bea4
Merge pull request #3537 from yfszzx/Inspiron
...
Move out images browser from project
3 years ago
734986dde3
add callback after image is saved
3 years ago
6cbb04f7a5
fix #3517 breaking txt2img
3 years ago
68931242cf
Merge branch 'AUTOMATIC1111:master' into Inspiron
3 years ago
e9a410b535
check length for variance
3 years ago
0d2e1dac40
convert deque -> list
...
I don't feel this being efficient
3 years ago
348f89c8d4
statistics for pbar
3 years ago
40b56c9289
cleanup some code
3 years ago
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
f2cc3f32d5
fix whitespaces
3 years ago
9741969325
Save properly processed image before color correction
3 years ago
a889c93f23
paste_fields add to public
3 years ago
cef1b89aa2
remove browser to extension
3 years ago
124e44cf1e
remove browser to extension
3 years ago
90f02c7522
Remove unused field and class
3 years ago
1e625624ba
Add folder processing endpoint
...
Also minor refactor
3 years ago
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.
3 years ago
e0ca4dfbc1
Update endpoints to use gradio's own utils functions
3 years ago
e3f0e34cd6
Merge branch 'master' of https://github.com/bamarillo/stable-diffusion-webui
3 years ago
4ff852ffb5
Add batch processing "extras" endpoint
3 years ago
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.
3 years ago
1be5933ba2
auto cropping now works with non square crops
3 years ago
6bd6154a92
Merge pull request #2067 from victorca25/esrgan_mod
...
update ESRGAN architecture and model to support all ESRGAN models
3 years ago
6a9ea40d7f
Move browser and Inspiration into extension
3 years ago
5dc0739ecd
working mask
3 years ago
9e1a8b7734
non-implemented mask with any type
3 years ago
a7c213d0f5
[API][Feature] - Add img2img API endpoint
3 years ago
1fbfc052eb
Update hypernetwork.py
3 years ago
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
3 years ago
b02926df13
Moved moodels to their own file and extracted base64 conversion to its own function
3 years ago
1b4d04737a
Remove unused imports
3 years ago
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.
3 years ago
ca5a9e79dc
fix for img2img color correction in a batch #3218
3 years ago
be748e8b08
add --freeze-settings commandline argument to disable changing settings
3 years ago
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
3 years ago
4fdb53c1e9
Generate grid preview for progress image
3 years ago
24694e5983
Update hypernetwork.py
3 years ago
321bacc6a9
call model_loaded_callback after setting shared.sd_model in case scripts refer to it using that
3 years ago
0df94d3fcf
fix aesthetic gradients doing nothing after loading a different model
3 years ago
324c7c732d
record First pass size as 0x0 for #3328
3 years ago
ffea9b1509
Merge pull request #3414 from discus0434/master
...
[Hypernetworks] Add a feature to use dropout / more activation functions
3 years ago
e38625011c
fix part2
3 years ago
72383abacd
Deepdanbooru linux fix
3 years ago
dbc8ab65f6
typo
3 years ago
d37cfffd53
added callback for creating new settings in extensions
3 years ago
6a4fa73a38
small fix
3 years ago
97749b7c7d
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
7912acef72
small fix
3 years ago
fccba4729d
add an option to avoid dying relu
3 years ago
7fd90128eb
added a guard for hypernet training that will stop early if weights are getting no gradients
3 years ago
1cd3ed7def
fix for extensions without style.css
3 years ago
dcb45dfecf
Merge branch 'master' of upstream
3 years ago
0e8ca8e7af
add dropout
3 years ago
50b5504401
remove parsing command line from devices.py
3 years ago
1fa53dab2c
Merge branch 'master' into cuda-device-id-selection
3 years ago
6398dc9b10
further support for extensions
3 years ago
2b91251637
removed aesthetic gradients as built-in
...
added support for extensions
3 years ago
AUTOMATIC1111
Martin Cairns
Jairo Correa
k_sugawara
timntorres
Roy Shilkrot
Fampai
Muhammad Rizqi Nur
DepFA
evshiron
Maiko Sinkyaet Tan
random_thoughtss
mawr
victorca25
aria1th
random-thoughtss
Bruno Seoane
timntorres
Bruno Seoane
Yaiol
Chris OBryan
benkyoujouzu
Antonio
Josh Watzman
FlameLaw
Florian Horn
yfszzx
guaneec
xmodar
MMaker
Sihan Wang
w-e-w
Milly
Stephen
captin411
brkirch
ritosonn
Trung Ngo
Vladimir Repin
Unnoen
MrCheeze
Greendayle
discus0434
discus0434