de5bfdf917
image info tab
...
* handles exceptions if jpeg jfif data not present
* removes further non-comment related exif data.
3 years ago
e49b1c5d73
an option to do exactly the amount of specified steps in img2img
3 years ago
2288bc96fd
fix extras tab showing original images instead of upscales
3 years ago
d8b427f8aa
remove the warning at startup related to previous PR with batch processing
3 years ago
b8cf2ea8ea
add a bit of a comment about what's being done with tensor noise
3 years ago
83bce1a604
Merge branch 'batch-seed-attempt'
3 years ago
87e8b9a2ab
prevent replacing torch_randn globally (instead replacing k_diffusion.sampling.torch) and add a setting to disable this all
3 years ago
b44ddcb443
Prompt editing only applies to images in first batch of desired batch size when batch count > 1 #535
3 years ago
b153ebe3b6
fix loopback color correction to store color_correction info for initial image and use that instead of extracting from previous image in a loop #481 #541
3 years ago
3763837003
Add batch processing to Extras tab
3 years ago
deea9f4d70
Replace invalid filename chars with an underscore
...
... instead of removing them altogether.
This makes the prompt editing filenames [old🆕 step] easier to read
3 years ago
6452fa2fb7
Merge remote-tracking branch 'origin/master'
3 years ago
6991f2cb27
SD upscale with Batch count>1 results broken images #512
3 years ago
2ddaeb318a
Update scripts.py
...
fixes bug #464 , which happens when controls is None, which leads to args_to being None.
3 years ago
0fde1f3eac
oh hey i broke batches with this
3 years ago
dc769e097c
Merge branch 'prompt_editing'
3 years ago
d4dc4c1c63
fix for Error Interrogating when user has garbage in text files #479
3 years ago
d7f7378828
quantization off by default
3 years ago
81baaff9b3
Respect quantization setting
3 years ago
829d7150bc
Add setting for quantization
3 years ago
3c37c68fe0
Construct CompVisDenoiser with quantization
3 years ago
cdaab233c4
Merge remote-tracking branch 'origin/master'
3 years ago
6d2eb339d6
fix for failing to save 4chan downscale for large iamges
3 years ago
9611008445
exif fix for webp
...
* fix for odd error only in webp files whereby piexif.insert inserts the bytes correctly, but image.save inserts extra "Exif" in the image metadata which results in an error on reading
3 years ago
72d7f8c761
fix typo
3 years ago
7ec6282ec2
pass dtype to torch.zeros as well
3 years ago
f2693bec08
prompt editing
3 years ago
b28cf84c36
prevent repeating messages about too many tokens
3 years ago
dfb2e830d9
Improved directory sanitization when --hide_ui_dir_config
...
Fixes an issue where it's still possible to write to arbitrary directories through careful use of \.. or /.. in directory patterns
...and fix the regex to work better
reeeegex
3 years ago
4a626f6ea6
Corrected typos in shared.py and README
3 years ago
5dde56afe3
Fixed typo in text attention setting
3 years ago
9f267af3f7
added a second style field
...
added the ability to use {prompt} in styles
added a button to apply style to textbox
rearranged top row for UI
3 years ago
6153d9d9e9
Update images.py
...
Better code
3 years ago
d5520d43fd
Update images.py
...
Handles grids names. Code more robust and doesn't fail if mixed with other files.
3 years ago
94aeb5dec9
Update images.py
...
Better computing of images indexes in filenames
3 years ago
3daf9cac46
Removed stray references to shared.device_codeformer.
3 years ago
26f733a026
fix for codeformer switching torch devices on metal systems.
3 years ago
bb2732c1c7
updates for exif comments #446
3 years ago
c4e90bf689
format exif string
...
* UserComment needs an ID code at the start of the tag area. This is provided by piexif.helper.UserComment, otherwise an "Warning Invalid EXIF text encoding for UserComment" is thrown upon reading the exif data
3 years ago
c9430e53f6
loopback moved to scripts, added support for multiple batches, changed to honor save grids and how grids in web setting
3 years ago
c253d6bdab
do not die on failing to load script #426
3 years ago
4c51752464
option name updates for #432
3 years ago
493032a7af
Update ui.py
3 years ago
df81de0d2f
Update ui.py
3 years ago
74c5f7974c
Added selected image saving
3 years ago
6bea45d495
prevent making grid if there is no need for it #428
3 years ago
f9f9d04b5f
prevent extras from saving in dir
...
Extras have none of the vars used in dir names, so they cant be saved into dirs.
+grid code cleanup
3 years ago
859fff3700
add webp to file formats with exif saved
3 years ago
f07d789b79
added cmd arg to load custom styles file
3 years ago
9d40212485
first attempt to produce crrect seeds in batch
3 years ago
85b97cc49c
bandaid for broken ddim sampling #389
3 years ago
950064ee96
img2img_color_correction off by default for #394
3 years ago
29022300ba
revert the breaking change in font sneaked in by the person who did EXIF #407
3 years ago
70e72db7bd
Merge remote-tracking branch 'origin/master'
3 years ago
b6b9faa779
add support for reading saved jpeg comments
3 years ago
7a5852a4ee
change np.float to np.float32
...
* numpy deprecation warning fix. Alternately, you could also specify float
3 years ago
27c2a0680a
save the exif data upon image write
3 years ago
34cf684419
add metadata to jpg and non-png image files
...
* needs a piexif module install
* dumps the info in an Exif "UserComment"
* update to webui.bat
3 years ago
3b1b1444d4
Complete cross attention update
3 years ago
c84e333622
color correction option for all img2img modes #363
3 years ago
823cf946ec
Embeddings directory can't be found if running webui.py from another directory (+potential fix) #374
3 years ago
b5a8b99d3f
put safety checker into a separate file because it's already crowded in processing
3 years ago
b03bc4e79a
Merge pull request #367 from GRMrGecko/nsfw_filter
...
Adds NSFW content filter option
3 years ago
3e1f9ab8b3
Fix #368
3 years ago
fc18e2d483
Adds NSFW content filter option
3 years ago
fa8be8acd6
Merge pull request #356 from nnuudev/master
...
Swap width and height sliders in the UI
3 years ago
db8f8dd972
Ability to save images into a folder named after the date they were created #353
3 years ago
19a817d97d
X/Y plot with denoising adds incorrect image data to individual outputs #331
3 years ago
0de109c210
Codeformer face restoration not working: AttributeError: module 'modules.shared' has no attribute 'device_codeformer' #348
3 years ago
a97e2a562b
Swap width and height sliders in the UI
3 years ago
3de44fc580
Include the model name (or the SHA256 of the file) in the metadata #271
3 years ago
c7e0e28ccd
changes for #294
3 years ago
11e03b9abd
Merge pull request #294 from EliasOenal/master
...
Fixes for mps/Metal: use of seeds, img2img, CodeFormer
3 years ago
a655e90fbe
add negative prompt to log when clicking save #249
3 years ago
45e8fa0e07
X/Y plot can not output the final result with this error message #244
3 years ago
482a6ce8cb
[Feature Request] Save defaults for extras & keep image parameters after using extras #251
3 years ago
843b2b64fc
Instance of CUDA out of memory on a low-res batch, even with --opt-split-attention-v1 (found cause) #255
3 years ago
75a9b1bbd9
Noisy image previews #257
3 years ago
40f4d3ed98
[FEATURE] Save both images, (Skip_Save optional). #265
3 years ago
b7f95869b4
Refactored Metal/mps fixes.
3 years ago
aaea8b4494
Update cross attention to the newest version
3 years ago
a5a760a7d4
rename --channelslast to --opt-channelslast to be in line with other torch optimizations
3 years ago
01f8de3229
Merge pull request #334 from C43H66N12O12S2/channels-last
...
Channels last support
3 years ago
b70b51cc72
Allow TF32 in CUDA for increased performance #279
3 years ago
8c995be44d
Add cmd option for channels last
3 years ago
11e648f6c7
allow resizing into non-integer sizes
3 years ago
a1305060ce
Variations are not working properly #305
3 years ago
264d255919
Merge pull request #329 from EyeDeck/master
...
Add --gradio-auth command line argument to enable Gradio authentication
3 years ago
a4416f3585
[BUG] Not Working As Intended - create a directory with name derived from the prompt #306
3 years ago
fc49844aa8
Merge branch 'master' into master
3 years ago
372a2c3e2e
[Feature Request] Please add "--share-password" for Gradio server security #315
3 years ago
e3646e79aa
Add --auth command line argument to enable Gradio authentication
...
Allows you to pass in Gradio authentication like:
`--auth username:password`
Supports multiple sets of credentials by comma-delimiting, like:
`--auth user1:pass1,user2:pass3`...
3 years ago
c094f00e10
Merge branch 'master' into master
3 years ago
ddc86f2edb
--gradio-debug for collab users
3 years ago
c50fa7a932
remove mistaken error message
3 years ago
e68484500f
Merge remote-tracking branch 'origin/master'
3 years ago
9bb20be090
memory optimization for CLIP interrogator
...
changed default cfg_scale to a higher value
3 years ago
655ef8e8cb
Added cmd arg to load custom ui settings file
3 years ago
ab0a79cdf4
keep interrogate models not in vram by default
3 years ago
e05e46aa3f
Merge branch 'master' into master
3 years ago
303b75c149
save sd upscales as samples not grids
3 years ago
81d91cea29
Merge remote-tracking branch 'origin/master'
3 years ago
4535239d8a
Add a samples filename format option
...
Adds a "samples filename format" option in the settings. This format can be defined by tags for maximum flexibility and scalability.
3 years ago
8fb9c57ed6
add half() supporrt for CLIP interrogation
3 years ago
29a2933e23
Add --hide-ui-dir-config command line flag
...
Adds `--hide-ui-dir-config` flag to disable editing directory configs from the web UI. This can be set to prevent users from setting the directory to somewhere they shouldn't, for public (or semi-public) interfaces.
Directories are still read from config.json, so the server admin can still set them in the web UI and then relaunch with the hide flag, or edit the config manually.
Also:
- fix OptionInfo `component_args` keyword argument not being read if `component` isn't also set
- ensure that hidden settings aren't still read from the web UI (otherwise they could still be changed by tampering with the interface)
3 years ago
5dc05c0d0d
Implemented workaround to allow the use of seeds with the mps/metal backend. Fixed img2img's use of unsupported precision float64 with mps backend.
3 years ago
2920ca7892
CodeFormer does not support mps/metal backend, implemented fallback to cpu backend.
3 years ago
cacd14bee8
Only create backup if path exists
3 years ago
5fbed65236
Add support for saving styles with negative prompts
3 years ago
f194457229
CLIP interrogator
3 years ago
13008bab90
Fixed prompt_style type hints: int -> str
3 years ago
f185874418
[Feature Request] Save defaults for extras & keep image parameters after using extras #251
3 years ago
2e6153e343
Merge remote-tracking branch 'origin/master'
3 years ago
a094b3ab8e
Add another instruction for workaround for #259
3 years ago
b5d1af11b7
Modular device management
3 years ago
065e310a3f
Change "send to "
3 years ago
06fadd2dc5
added --opt-split-attention-v1
3 years ago
77f8a72fa8
fix a bug with error message
3 years ago
1b963c205f
fixed broken empty directory when prompt does not start with letter, this time for real
3 years ago
b3311a50dc
fix repeating subseeds for every batch #221
3 years ago
43bdbe934a
enabled negative prompt by default
...
fixed broken empty directory when prompt does not start withl etter
3 years ago
13eec4f3d4
changed <p> to <br> in info field to prevent double line breaks when copying
...
added new features to the list.
3 years ago
4d2c0c7a72
undo CodeFormer's upscaling of images with dimensions less than 512.
3 years ago
decbbe81f5
separated options for sample and grid dir saving for #222
3 years ago
c92f2ff196
Update to cross attention from https://github.com/Doggettx/stable-diffusion #219
3 years ago
ef0cdb8a42
add batch count to sd upscale #169
...
fix writing empty prompt pictures to rroot directory instead of 'empty'
suppress 'Denoising strength change factor' text inimage info unless using loopback mode
3 years ago
955f644ce1
split settings into three columns
...
added a different workaround for gradio mask bug with info in UI
switched to newer gradio version
3 years ago
695c05fb30
prioritize repositories/stable-diffusion path when searching for SD
3 years ago
6f678ec79c
Emoji are not being sorted correctly #192
3 years ago
26ce47eb6c
[Feature Request] Ability to pass a custom ui-config.json via command line args #212
3 years ago
1fcb48347d
prevent styles from adding an extra comma
3 years ago
fbdec2ef20
Fix prompt matrix script
3 years ago
89f4bb3ca1
Cleaner condition
3 years ago
79cca25704
Embed roboto
3 years ago
86867e153f
support for prompt styles
...
fix broken prompt matrix
3 years ago
d714ea4c41
ability to upload mask for inpainting
3 years ago
5b6a585ae5
Merge remote-tracking branch 'origin/master' into seeds
3 years ago
17a7477c72
Include negative prompt in parameters text file
3 years ago
b1707553cf
added resize seeds and variation seeds features
3 years ago
003b60b94e
add an option to show negative prompt
3 years ago
bcb8a5eb0a
change default font capitalization to possibly help linux users #157
3 years ago
116a2b89c0
Merge pull request #167 from orionaskatu/patch-1
...
Some typos
3 years ago
93524bfb73
Merge pull request #153 from SafentisFox/fix_output_display
...
Fix webui.bat ignoring cmd line arguments, fix output img overflowing
3 years ago
764a64b02e
Some typos
3 years ago
fe4e3c2673
fix for PLMS live previews in txt2img
3 years ago
ca3861e05f
fix for DDIM live previews in txt2img
3 years ago
701f76b29a
Merge pull request #158 from JohannesGaessler/progress-printing
...
More informative progress printing
3 years ago
f211c498b9
More informative progress printing
3 years ago
20b86e81c3
Merge pull request #154 from rewbs/img2img2-loopback-denoise-strength-change-factor
...
Turn the loopback denoising strength change factor into a parameter rather than hardcoding to 0.95. Set the default to 1.
3 years ago
ad02b249f5
add a helpful message when user puts RealESRGAN model into ESRGAN directory.
3 years ago
62ce77e245
support for sd-concepts as alternatives for textual inversion #151
3 years ago
f5001246e2
honor tiling settings for RealESRGAN also
...
load scripts earlier to get errors before model loads
3 years ago
6dc5cf558d
Fix webui.bat ignoring cmd line arguments, fix output img overflowing
3 years ago
ed01f69542
Turn the loopback denoise strength change factor into a parameter rather than hardcoding to 0.95. Set the default to 1.
3 years ago
567c1fbc1c
Port defaults to none
3 years ago
db92896e30
help message for ports < 1024
3 years ago
5d087731a5
add --port argument to shared.py
...
defaults to 7860
3 years ago
61785cef65
Merge remote-tracking branch 'origin/master'
3 years ago
0fedd50886
another change for inpainting at full resolution
3 years ago
21a375e6b2
Merge branch 'master' into img2img2-color-correction
3 years ago
1e7a36fd79
Remove debug print.
3 years ago
52e071da2a
Add color correction to img2img loopback to avoid a progressive skew to magenta. Based on codedealer's PR to hlky's repo here: https://github.com/sd-webui/stable-diffusion-webui/pull/698/files .
3 years ago
7045c84643
Also use alpha channel from img2img input image as mask
3 years ago
296d012423
Merge pull request #108 from xeonvs/mps-support
...
Added support for launching on Apple Silicon M1/M2
3 years ago
ba1124b326
directly convert list to tensor
3 years ago
aaeeef82fa
Miss device type for option --medvram
3 years ago
700c47a674
big improvements to inpainting and outpainting
3 years ago
65fbefd033
Added support for launching on Apple Silicon
3 years ago
15bb8e8057
labeling updates according to anon's feedback
3 years ago
8dcd3e57e7
a little bit of rework for extras tab
3 years ago
5e12c23a67
clarification for settings; another comment about copied files
3 years ago
6a9b33c848
codeformer support
3 years ago
6521f90fa2
add a font for google collab
3 years ago
23ee74e9e3
fix error with --help #91
3 years ago
a1743e4518
remove double basicr requirement
...
add seed change for anon
3 years ago
a8504157a0
some changes for outpainting to produce less seams
3 years ago
7ce7fb01e0
fix for live progress breaking lowvram and medvram optimizations
3 years ago
7e5b8becf9
fix for progress bar
3 years ago
fd66199769
added preview option
3 years ago
66a9ca9d00
fixes for incorrect progressbar
3 years ago
5e20657146
fix grid overwriting bug
3 years ago
3f55d9a932
collab link
3 years ago
c688d0984e
some extra changes for collab compatibility
3 years ago
395f170597
readme extras for VRAM for
...
added missing packages to requirements for #74
add support for negative numbers in X/Y plot (plus ranges) #73
changed progressbar to work properly with custom modes
3 years ago
a243bc7859
added progressbar
...
added an option to disable progressbar
added interrupt support to DDIM/PLMS
3 years ago
b6763fb884
added random artist button
...
added a setting for padding when doing inpaint at original resolution
3 years ago
f5563853b8
add information about batch to the image
3 years ago
064965c466
added --listen option to make gradio listen on network requests
3 years ago
5bb69bd915
fix for setting values for gradio sliders when users has bad data in ui-config.json
3 years ago
a8a58dbac7
re-integrated tiling option as a UI element
3 years ago
f91d0c3d19
add an option to enable tiling image generation
3 years ago
a039878c0f
bugfix (thx #88443949 )
3 years ago
5bb126bd89
add split attention layer optimization from https://github.com/basujindal/stable-diffusion/pull/117
3 years ago
f299645aee
ESRGAN support
3 years ago
78278ce695
added UI config file: ui-config.json
3 years ago
7350c71259
added poor man's inpainting script
3 years ago
b608222d25
fix for broken image saving when using non-default directory
3 years ago
657074a73d
option to invert mask for inpainting
3 years ago
e67a56dbb4
fix to make scripts that failed to compile not crash the program
3 years ago
226de5e503
Merge pull request #60 from hentailord85ez/file-not-found-fix
...
Don't iterate over scripts if it doesn't exist
3 years ago
592334f322
scripts
3 years ago
26404eaabf
Don't iterate over scripts if it doesn't exist
3 years ago
595c827bd3
option to unload GFPGAN after using
3 years ago
f40617d6c4
support for scripts
3 years ago
345028099d
split codebase into multiple files; to anyone this affects negatively: sorry
3 years ago
JJ
AUTOMATIC
ArrowM
Twizzes
OWKenobi
C43H66N12O12S2
EyeDeck
Steve Eberhardt
NebulousDev
Michoko
Elias Oenal
jtkelm2
JustAnOkapi
camenduru
oobabooga
GRMrGecko
nnuudev
Stephan Reinwald
cryzed
JohannesGaessler
Abdullah Barhoum
Seki
Lukas Meller
orionaskatu
David Yates
safentisAuth
rewbs
fuzzytent
xeonvs
hentailord85ez