2016733814
Apply hijacks in ddpm_edit for upcast sampling
...
To avoid import errors, ddpm_edit hijacks are done after an instruct pix2pix model is loaded.
3 years ago
4738486d8f
Support for hypernetworks with --upcast-sampling
3 years ago
5d483bf307
aspect ratio for dim's; sliders adjust by ratio
...
Default choices added to settings in user interface section
Choices are editable by user
User selects from dropdown.
When you move one slider, the other adjusts according to the ratio
chosen.
Vice versa for the other slider.
Number fields for changes work as well.
For disabling ratio, an unlock pad "🔓 " is available as a default.
This string can be changed to anything to serve as a disable,
as long as there is no colon ":".
Ratios are entered in this format, floats or ints with a colon "1:1".
The string is split at the colon, parses left and right as floats to
perform the math.
3 years ago
9a22c63f47
call modules.sd_vae.refresh_vae_list()
3 years ago
584f782391
Update ui_extra_networks.py
...
update the string used to build the ID handle to replace spaces with underscore
3 years ago
fe33be6cac
use Default if ValueError
3 years ago
6d11cda418
configurable image downscale
...
allowing the user to configure the image downscale parameters in setting
3 years ago
0ca1a64cfc
adds grid margins to xyz plot and prompt matrix
3 years ago
3993aa43e9
Merge pull request #7535 from mcmonkey4eva/fix-symlink-extra-network
...
fix symlinks in extra networks ui
3 years ago
27a50d4b38
Merge pull request #7554 from techneconn/feature/prompt_hash_option
...
Add prompt_hash option for file/dir name pattern
3 years ago
475095f50a
Merge pull request #7528 from spezialspezial/patch-1
...
Catch broken model symlinks early | Quickfix modelloader.py
3 years ago
668d7e9b9a
make it possible to load SD1 checkpoints without CLIP
3 years ago
5a1b62e9f8
Add prompt_hash option for file/dir name pattern
3 years ago
88a46e8427
fix symlinks in extra networks ui
...
'absolute' and 'resolve' are equivalent, but 'resolve' resolves symlinks (which is an obscure specialty behavior usually not wanted) whereas 'absolute' treats symlinks as folders (which is the expected behavior). This commit allows you to symlink folders within your models/embeddings/etc. dirs and have preview images load as expected without issue.
3 years ago
6524478850
Update modelloader.py
...
os.path.getmtime(filename) throws exception later in codepath when meeting broken symlink. For now catch it here early but more checks could be added for robustness.
3 years ago
3e0f9a7543
fix issue with switching back to checkpoint that had its checksum calculated during runtime mentioned in #7506
3 years ago
40e51fd6ef
add margin parameter to draw_grid_annotations
3 years ago
21593c8082
Merge pull request #7466 from ctwrs/master
...
Add .jpg to allowed thumb formats
3 years ago
c0e0b5844d
Merge pull request #7470 from cbrownstein-lambda/update-error-message-no-checkpoint
...
Update error message WRT missing checkpoint file
3 years ago
81823407d9
add --no-hashing
3 years ago
30228c67ca
Merge pull request #7461 from brkirch/mac-fixes
...
Move Mac related code to separate file
3 years ago
c4b9ed1a27
make Image CFG Scale only show if instrutpix2pix model is loaded
3 years ago
72dd5785d9
merge CFGDenoiserEdit and CFGDenoiser into single object
3 years ago
4306659c4d
Remove unused code
3 years ago
ba6a4e7e94
Use original CFGDenoiser if image_cfg_scale = 1
...
If image_cfg_scale is =1 then the original image is not used for the output. We can then use the original CFGDenoiser to get the same result to support AND functionality.
Maybe in the future AND can be supported with "Image CFG Scale"
3 years ago
c27c0de0f7
txt2img Hires Fix
3 years ago
6c6c6636bb
Image CFG Added (Full Implementation)
...
Uses separate denoiser for edit (instruct-pix2pix) models
No impact to txt2img or regular img2img
"Image CFG Scale" will only apply to instruct-pix2pix models and metadata will only be added if using such model
3 years ago
3b2ad20ac1
Processing only, no CFGDenoiser change
...
Allows instruct-pix2pix
3 years ago
cf0cfefe91
Revert "instruct-pix2pix support"
...
This reverts commit 269833067d
3 years ago
269833067d
instruct-pix2pix support
3 years ago
fb97acef63
Update error message WRT missing checkpoint file
...
The Safetensors format is also supported.
3 years ago
92bae77b88
Add .jpg to allowed thumb formats
3 years ago
1b8af15f13
Refactor Mac specific code to a separate file
...
Move most Mac related code to a separate file, don't even load it unless web UI is run under macOS.
3 years ago
07edf57409
Merge pull request #7357 from EllangoK/btn-fix
...
Fixes switch height/width btn unbound error
3 years ago
30a64504b1
Merge pull request #7414 from joecodecreations/master
...
Changes use_original_name_batch to default to True
3 years ago
2217331cd1
Refactor MPS fixes to CondFunc
3 years ago
7738c057ce
MPS fix is still needed :(
...
Apparently I did not test with large enough images to trigger the bug with torch.narrow on MPS
3 years ago
0426b34789
Adding default true to use_original_name_batch as images should by default hold the same name to help keep sequenced images in their correct order
3 years ago
ee9fdf7f62
Add --skip-version-check to disable messages asking users to upgrade torch.
3 years ago
ab059b6e48
make the program read Discard penultimate sigma from generation parameters
3 years ago
040ec7a80e
make the program read Eta and Eta DDIM from generation parameters
3 years ago
4df63d2d19
split samplers into one more files for k-diffusion
3 years ago
274474105a
Split history sd_samplers.py to sd_samplers_kdiffusion.py
3 years ago
95916e3777
Split history sd_samplers.py to sd_samplers_kdiffusion.py
3 years ago
2db8ed32cd
Split history sd_samplers.py to sd_samplers_kdiffusion.py
3 years ago
f4d0538bf2
Split history sd_samplers.py to sd_samplers_kdiffusion.py
3 years ago
aa54a9d416
split compvis sampler and shared sampler stuff into their own files
3 years ago
f8fcad502e
Split history sd_samplers.py to sd_samplers_common.py
3 years ago
58ae93b954
Split history sd_samplers.py to sd_samplers_common.py
3 years ago
6e78f6a896
Split history sd_samplers.py to sd_samplers_common.py
3 years ago
5feae71dd2
Split history sd_samplers.py to sd_samplers_common.py
3 years ago
449531a6c5
Split history sd_samplers.py to sd_samplers_compvis.py
3 years ago
9b8ed7f8ec
Split history sd_samplers.py to sd_samplers_compvis.py
3 years ago
9118b08606
Split history sd_samplers.py to sd_samplers_compvis.py
3 years ago
0c7c36a6c6
Split history sd_samplers.py to sd_samplers_compvis.py
3 years ago
c81b52ffbd
add override settings component to img2img
3 years ago
847ceae1f7
make it possible to search checkpoint by its hash
3 years ago
399720dac2
update prompt token counts after using the paste params button
3 years ago
f91068f426
change disable_weights_auto_swap to true by default
3 years ago
938578e8a9
make it so that setting options in pasted infotext (like Clip Skip and ENSD) do not get applied directly and instead are added as temporary overrides
3 years ago
00dab8f10d
remove Batch size and Batch pos from textinfo (goodbye)
3 years ago
aa6e55e001
do not display the message for TI unless the list of loaded embeddings changed
3 years ago
920fe8057c
fixes #7284 btn unbound error
3 years ago
8d7382ab24
add buttons for auto-search in subdirectories for extra tabs
3 years ago
e8efd2ec47
Merge pull request #7353 from EllangoK/preview-fix
...
Fixes thumbnail cards not loading the preview image
3 years ago
659d602dce
only returns ckpt directories if they are not none
3 years ago
f6b7768f84
support for searching subdirectory names for extra networks
3 years ago
09a142a05a
Reduce grid rows if larger than number of images available
...
When a set number of grid rows is specified in settings, then it leads
to situations where an entire row in the grid is empty.
The most noticable example is the processing preview when the row count
is set to 2, where it shows the preview just fine but with a black
rectangle under it.
3 years ago
1d8e06d542
add checkpoints tab for extra networks UI
3 years ago
91c8d0dcfc
Merge pull request #7231 from EllangoK/master
...
Fixes X/Y/Z Plot parameters not being restored from images
3 years ago
fecb990deb
Merge pull request #7309 from brkirch/fix-embeddings
...
Fix embeddings, upscalers, and refactor `--upcast-sampling`
3 years ago
e2c71a4bd4
make prevent the browser from using cached version of scripts when they change
3 years ago
591b68e56c
uses autos new regex, checks len of re_param
3 years ago
cd7e8fb42b
Merge pull request #7319 from Thurion/img2img_batch_fix
...
Fix error when using img2img batch without masks
3 years ago
b7d2af8c7f
add dropdowns in settings for hypernets and loras
3 years ago
1421e95960
allow empty mask dir
3 years ago
5d14f282c2
fixed a bug where after switching to a checkpoint with unknown hash, you'd get empty space instead of checkpoint name in UI
...
fixed a bug where if you update a selected checkpoint on disk and then restart the program, a different checkpoint loads, but the name is shown for the the old one.
3 years ago
f8feeaaedb
add progressbar to extension update check; do not check for updates for disabled extensions
3 years ago
d04e3e921e
automatically detect v-parameterization for SD2 checkpoints
3 years ago
4aa7f5b5b9
update image parameters regex for #7231
3 years ago
f9edd578e9
Remove MPS fix no longer needed for PyTorch
...
The torch.narrow fix was required for nightly PyTorch builds for a while to prevent a hard crash, but newer nightly builds don't have this issue.
3 years ago
ada17dbd7c
Refactor conditional casting, fix upscalers
3 years ago
bea31e849a
Merge pull request #7240 from Unstackd/master
...
Allow users to convert models to Instruct-pix2pix models by supporting merging Instruct-pix2pix models with regular ones in the merge tab
3 years ago
3752aad23d
don't replace regular --help with new paths.py parser help
3 years ago
dc25a31d1a
Gradio Auth Read from External File
...
Usage: `--gradio-auth-path {PATH}`
It adds the credentials to the already existing `--gradio-auth` credentials. It can also handle line breaks.
The file should look like:
`{u1}:{p1},{u2}:{p2}`
or
```
{u1}:{p1},
{u2}:{p2}
```
Will gradio handle duplicate credentials if it happens?
3 years ago
ce72af87d3
Merge pull request #7199 from maxaudron/feature/configurable-data-dir
...
Add flag to store user data sepperate from source code
3 years ago
0834d4ce37
simplify #7284
3 years ago
c99d705e57
Merge pull request #7284 from Gazzoo-byte/patch-1
...
Add button to switch width and height
3 years ago
4c52dfe4ac
make the detection for -v models less broad
3 years ago
41975c375c
Merge pull request #7294 from MrCheeze/model-detection
...
add v2-inpainting model detection, and broaden v-model detection to include anything with 768 in the name
3 years ago
2aac1d9778
Basic inpainting batch support
...
Modifies batch UI to add optional inpainting support
3 years ago
6b82efd737
add v2-inpainting model detection, and broaden v-model detection to include anything with 768 in the name
3 years ago
cc8c9b7474
fix broken calls to find_checkpoint_config
3 years ago
eafaf14167
Add button to switch width and height
...
Adds a button to switch width and height, allowing quick and easy switching between landscape and portrait.
3 years ago
23a9d5e273
create user extensions directory if not exists
3 years ago
6b3981c068
clean up unused script_path imports
3 years ago
14c0884fd0
use python importlib to load and execute extension modules
...
previously module attributes like __file__ where not set correctly,
leading to scripts getting the directory of the stable-diffusion repo
location instead of their own script.
This causes problem when loading user data from an external location
using the --data-dir flag, as extensions would look for their own code
in the stable-diffusion repo location instead of the data dir location.
Using pythons importlib functions sets the modules specs correctly and
executes them. But this will break extensions if they build paths based
on the previously incorrect __file__ attribute.
3 years ago
5eee2ac398
add data-dir flag and set all user data directories based on it
3 years ago
9beb794e0b
clarify the option to disable NaN check.
3 years ago
6f31d2210c
support detecting midas model
...
fix broken api for checkpoint list
3 years ago
d2ac95fa7b
remove the need to place configs near models
3 years ago
7a14c8ab45
add an option to enable sections from extras tab in txt2img/img2img
...
fix some style inconsistenices
3 years ago
cdc2fa209a
Changed filename addition from "instrpix2pix" to the more readable ".instruct-pix2pix" for newly generated instruct pix2pix models.
3 years ago
c4b9b07db6
Fix embeddings dtype mismatch
3 years ago
9e72dc7434
Changed all references to "pix2pix" to the more precise name "instruct pix2pix". Also changed extension to instrpix2pix at least for now.
3 years ago
f90798c6b6
Added error check for the rare case a user merges a pix2pix model with a normal model using weighted sum. Also removed bad print message that interfered with merging progress bar.
3 years ago
f4ec411f2c
Allow checkpoint merger to merge pix2pix models in the same way that it currently supports inpainting models.
3 years ago
10421f93c3
Fix full previews, --no-half-vae
3 years ago
4d634dc592
adds components to infotext_fields
...
allows for loading script params
3 years ago
e57b5f7c55
re_param captures quotes with commas properly
...
and removes unnecessary regex
3 years ago
6cff440182
fix prompt editing break after first batch in img2img
3 years ago
d1d6ce2983
add edit_image_conditioning from my earlier edits in case there's an attempt to inegrate pix2pix properly
...
this allows to use pix2pix model in img2img though it won't work well this way
3 years ago
3cead6983e
Merge pull request #7197 from mcmonkey4eva/fix-ti-symlinks
...
allow symlinks in the textual inversion embeddings folder
3 years ago
15e89ef0f6
fix for unet hijack breaking the train tab
3 years ago
789d47f832
make clicking extra networks button one more time close the extra networks UI
3 years ago
e179b6098a
allow symlinks in the textual inversion embeddings folder
3 years ago
1574e96729
Merge pull request #6510 from brkirch/unet16-upcast-precision
...
Add upcast options, full precision sampling from float16 UNet and upcasting attention for inference using SD 2.1 models without --no-half
3 years ago
57c1baa774
change to code for live preview fix on OSX to be bit more obvious
3 years ago
23dafe6d86
Merge pull request #7151 from brkirch/fix-approx-nn
...
Fix Approx NN previews changing first generation result
3 years ago
ee0a0da324
Add instruct-pix2pix hijack
...
Allows loading instruct-pix2pix models via same method as inpainting models in sd_models.py and sd_hijack_ip2p.py
Adds ddpm_edit.py necessary for instruct-pix2pix
3 years ago
d5ce044bcd
Merge pull request #7146 from EllangoK/master
...
Adds X/Y/Z Grid Script
3 years ago
e3b53fd295
Add UI setting for upcasting attention to float32
...
Adds "Upcast cross attention layer to float32" option in Stable Diffusion settings. This allows for generating images using SD 2.1 models without --no-half or xFormers.
In order to make upcasting cross attention layer optimizations possible it is necessary to indent several sections of code in sd_hijack_optimizations.py so that a context manager can be used to disable autocast. Also, even though Stable Diffusion (and Diffusers) only upcast q and k, unfortunately my findings were that most of the cross attention layer optimizations could not function unless v is upcast also.
3 years ago
84d9ce30cb
Add option for float32 sampling with float16 UNet
...
This also handles type casting so that ROCm and MPS torch devices work correctly without --no-half. One cast is required for deepbooru in deepbooru_model.py, some explicit casting is required for img2img and inpainting. depth_model can't be converted to float16 or it won't work correctly on some systems (it's known to have issues on MPS) so in sd_models.py model.depth_model is removed for model.half().
3 years ago
5228ec8bda
remove fairscale requirement, add fake fairscale to make BLIP not complain about it mk2
3 years ago
28189985e6
remove fairscale requirement, add fake fairscale to make BLIP not complain about it
3 years ago
e46bfa5a9e
handling sub grids and merging into one
3 years ago
602a1864b0
also return the removed field to sdapi/v1/upscalers because someone might have relied on it existing
3 years ago
42a70d7477
repair sdapi/v1/upscalers returning bogus results
3 years ago
f64af77adc
Fix different first gen with Approx NN previews
...
The loading of the model for approx nn live previews can change the internal state of PyTorch, resulting in a different image. This can be avoided by preloading the approx nn model in advance.
3 years ago
45e270dfc8
add image decod exception handling
3 years ago
5c1cb9263f
fix BLIP failing to import depending on configuration
3 years ago
7ba7f4ed6e
Merge pull request #7113 from vladmandic/interrogate
...
Add selector to interrogate categories
3 years ago
7b1c7ba87b
add support for apostrophe in extra network names
3 years ago
04a561c11c
add option to skip interrogate categories
3 years ago
efa7287be0
Merge branch 'AUTOMATIC1111:master' into interrogate
3 years ago
171a5b3bb9
Merge pull request #7032 from gmq/extra-network-styles
...
Extra network view style
3 years ago
6e1b296baf
api-image-format
3 years ago
e8c3d03f7d
a possible fix for broken image upscaling
3 years ago
925dd09c91
improve interrogate
3 years ago
59146621e2
better support for xformers flash attention on older versions of torch
3 years ago
3fa482076a
Merge remote-tracking branch 'takuma104/xformers-flash-attention'
3 years ago
194cbd065e
fix open directory button failing
3 years ago
663353098e
Merge pull request #7031 from EllangoK/master
...
Fixes various button overflowing UI and compact checkbox
3 years ago
74608300d1
Merge pull request #7093 from Shondoit/fix-dark-mode
...
Fix dark mode
3 years ago
41265a026d
third time's the charm
3 years ago
fabdae089e
add missing import to previous commit
3 years ago
669dbd9725
Fix dark mode
...
Fixes #7048
Co-Authored-By: J.J. Tolton <jjtolton@gmail.com>
3 years ago
b5230197a6
rework extras tab to use script system
3 years ago
f80ff3c1e4
feat(extra-networks): remove view dropdown
3 years ago
66eef11ce7
feat(extra-networks): add default view setting
3 years ago
985c0b8e9a
feat(extra-networks): add thumbs view style
3 years ago
68303c96e5
split oversize extras.py to postprocessing.py
3 years ago
c56b367122
Split history extras.py to postprocessing.py
3 years ago
d63340a485
Split history extras.py to postprocessing.py
3 years ago
b238b14ee4
Split history extras.py to postprocessing.py
3 years ago
43ac9ff205
Split history extras.py to postprocessing.py
3 years ago
c98cb0f8ec
amend previous commit to work in a proper fashion when saving previews
3 years ago
35419b2746
add an option to reorder tabs for extra networks
3 years ago
112416d041
add option to discard weights in checkpoint merger UI
3 years ago
0792fae078
fix missing field for aesthetic embedding extension
3 years ago
2621566153
attention ctrl+up/down enhancements
3 years ago
bf457b30fb
compact checkbox and fix copy image btn overflow
...
also fixes type for #tab_extensions in style.css
3 years ago
f2eae6127d
fix broken textual inversion extras tab
3 years ago
fe7a623e6b
add a slider for default value of added extra networks
3 years ago
78f59a4e01
enable compact view for train tab
...
prevent previews from ruining hypernetwork training
3 years ago
abf11215e0
Merge pull request #6955 from EllangoK/master
...
Adds descriptions for merging methods in UI
3 years ago
4a8fe09652
remove the double loading text
3 years ago
e4e0918f58
remove timestamp for js files, reformat code
3 years ago
7c8852b8e7
Merge pull request #7015 from jjtolton/serve-static-js
...
Compile and serve js files via `src` instead of embedded inline scripts
3 years ago
035459c9a2
remove dead import
3 years ago
50059ea661
server individually listed javascript files vs single compiled file
3 years ago
17af0fb955
remove commented out lines
3 years ago
f726df8a2f
Compile and serve js from /statica instead of inline in html
3 years ago
f53527f778
make it run on gradio < 3.16.2
3 years ago
3deea34135
extract extra network data from prompt earlier
3 years ago
63b824376c
add --gradio-queue option to enable gradio queue
3 years ago
424cefe118
add search box to extra networks
3 years ago
92fb1096db
make it so that extra networks are not removed from infotext
3 years ago
855b9e3d1c
Lora support!
...
update readme to reflect some recent changes
3 years ago
3262e825cc
add --xformers-flash-attention option & impl
3 years ago
184e23eb89
relocate tool buttons next to generate button
...
prevent extra network tabs from putting images into wrong prompts
prevent settings leaking into prompt
3 years ago
6d805b669e
make CLIP interrogator download original text files if the directory does not exist
...
remove random artist built-in extension (to re-added as a normal extension on demand)
remove artists.csv (but what does it mean????????????????????)
make interrogate buttons show Loading... when you click them
3 years ago
40ff6db532
extra networks UI
...
rework of hypernets: rather than via settings, hypernets are added directly to prompt as <hypernet:name:weight>
3 years ago
20a59ab3b1
move token counter to the location of the prompt, add token counting for the negative prompt
3 years ago
98466da4bc
adds descriptions for merging methods in ui
3 years ago
6c7a50d783
remove some unnecessary logging to javascript console
3 years ago
6073456c83
write a comment for fix_checkpoint function
3 years ago
51517f3ea6
Merge pull request #6936 from EllangoK/master
...
Fixes minor typos around run_modelmerger
3 years ago
c1928cdd61
bring back short hashes to sd checkpoint selection
3 years ago
f2ae252987
fixes minor typos around run_modelmerger
3 years ago
d1ea518dea
remember the list of checkpoints after you press refresh button and reload the page
3 years ago
b271e22f7a
Update shared.py
...
`Witdth/Height` was driving me insane. -> `Width/Height`
3 years ago
aa60fc6660
Merge pull request #6922 from brkirch/cumsum-fix
...
Improve cumsum fix for MPS
3 years ago
0f9cacaa0e
Merge pull request #6844 from guaneec/crop-ui
...
Add auto-sized cropping UI
3 years ago
2985b317d7
Fix of fix
3 years ago
18a09c7e00
Simplification and bugfix
3 years ago
54674674b8
allow having at half precision when there is only one checkpoint in merger tab
3 years ago
0f5dbfffd0
allow baking in VAE in checkpoint merger tab
...
do not save config if it's the default for checkpoint merger tab
change file naming scheme for checkpoint merger tab
allow just saving A without any merging for checkpoint merger tab
some stylistic changes for UI in checkpoint merger tab
3 years ago
c7e50425f6
add progress bar to modelmerger
3 years ago
7cfc645030
eliminate repetition of code in #6910
3 years ago
brkirch
Gerschel
EllangoK
CurtisDS
w-e-w
AUTOMATIC1111
techneconn
Alex "mcmonkey" Goodwin
spezialspezial
Kyle
Cody Brownstein
ctwrs
Joey Sanchez
glop102
Thurion
Mackerel
Ju1-js
Andrii Skaliuk
MrCheeze
Gazzoo-byte
Max Audron
ULTRANOX\Chris
Vladimir Mandic
Shondoit
Guillermo Moreno
James Tolton
Takuma Mori
vt-idiot
dan