6f31d2210c
support detecting midas model
...
fix broken api for checkpoint list
2023-01-27 11:54:19 +03:00
d2ac95fa7b
remove the need to place configs near models
2023-01-27 11:28:12 +03:00
7a14c8ab45
add an option to enable sections from extras tab in txt2img/img2img
...
fix some style inconsistenices
2023-01-26 23:31:32 +03:00
cdc2fa209a
Changed filename addition from "instrpix2pix" to the more readable ".instruct-pix2pix" for newly generated instruct pix2pix models.
2023-01-26 11:27:07 -05:00
c4b9b07db6
Fix embeddings dtype mismatch
2023-01-26 09:00:15 -05:00
9e72dc7434
Changed all references to "pix2pix" to the more precise name "instruct pix2pix". Also changed extension to instrpix2pix at least for now.
2023-01-26 06:05:40 -05:00
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.
2023-01-26 04:38:04 -05:00
f4ec411f2c
Allow checkpoint merger to merge pix2pix models in the same way that it currently supports inpainting models.
2023-01-26 03:45:16 -05:00
10421f93c3
Fix full previews, --no-half-vae
2023-01-26 01:43:35 -05:00
4d634dc592
adds components to infotext_fields
...
allows for loading script params
2023-01-26 00:18:41 -05:00
e57b5f7c55
re_param captures quotes with commas properly
...
and removes unnecessary regex
2023-01-25 22:36:14 -05:00
6cff440182
fix prompt editing break after first batch in img2img
2023-01-25 23:25:40 +03:00
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
2023-01-25 23:25:25 +03:00
3cead6983e
Merge pull request #7197 from mcmonkey4eva/fix-ti-symlinks
...
allow symlinks in the textual inversion embeddings folder
2023-01-25 22:59:12 +03:00
15e89ef0f6
fix for unet hijack breaking the train tab
2023-01-25 20:11:01 +03:00
789d47f832
make clicking extra networks button one more time close the extra networks UI
2023-01-25 19:55:31 +03:00
e179b6098a
allow symlinks in the textual inversion embeddings folder
2023-01-25 08:48:40 -08:00
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
2023-01-25 19:12:29 +03:00
57c1baa774
change to code for live preview fix on OSX to be bit more obvious
2023-01-25 18:56:23 +03:00
23dafe6d86
Merge pull request #7151 from brkirch/fix-approx-nn
...
Fix Approx NN previews changing first generation result
2023-01-25 18:48:25 +03:00
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
2023-01-25 08:53:23 -05:00
d5ce044bcd
Merge pull request #7146 from EllangoK/master
...
Adds X/Y/Z Grid Script
2023-01-25 11:56:26 +03:00
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.
2023-01-25 01:13:04 -05:00
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().
2023-01-25 01:13:02 -05:00
5228ec8bda
remove fairscale requirement, add fake fairscale to make BLIP not complain about it mk2
2023-01-24 20:30:43 +03:00
28189985e6
remove fairscale requirement, add fake fairscale to make BLIP not complain about it
2023-01-24 20:24:27 +03:00
44c0e6b993
Merge branch 'AUTOMATIC1111:master' into master
2023-01-24 15:44:09 +03:00
e46bfa5a9e
handling sub grids and merging into one
2023-01-24 02:24:32 -05:00
602a1864b0
also return the removed field to sdapi/v1/upscalers because someone might have relied on it existing
2023-01-24 10:09:30 +03:00
42a70d7477
repair sdapi/v1/upscalers returning bogus results
2023-01-24 10:05:45 +03:00
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.
2023-01-23 22:49:20 -05:00
45e270dfc8
add image decod exception handling
2023-01-23 17:11:22 -05:00
5c1cb9263f
fix BLIP failing to import depending on configuration
2023-01-24 00:24:17 +03:00
7ba7f4ed6e
Merge pull request #7113 from vladmandic/interrogate
...
Add selector to interrogate categories
2023-01-24 00:09:14 +03:00
7b1c7ba87b
add support for apostrophe in extra network names
2023-01-23 23:11:34 +03:00
04a561c11c
add option to skip interrogate categories
2023-01-23 12:29:23 -05:00
efa7287be0
Merge branch 'AUTOMATIC1111:master' into interrogate
2023-01-23 12:25:07 -05:00
171a5b3bb9
Merge pull request #7032 from gmq/extra-network-styles
...
Extra network view style
2023-01-23 18:46:37 +03:00
6e1b296baf
api-image-format
2023-01-23 10:10:59 -05:00
e8c3d03f7d
a possible fix for broken image upscaling
2023-01-23 17:59:58 +03:00
925dd09c91
improve interrogate
2023-01-23 09:03:17 -05:00
59146621e2
better support for xformers flash attention on older versions of torch
2023-01-23 16:40:20 +03:00
3fa482076a
Merge remote-tracking branch 'takuma104/xformers-flash-attention'
2023-01-23 16:01:53 +03:00
194cbd065e
fix open directory button failing
2023-01-23 15:50:32 +03:00
663353098e
Merge pull request #7031 from EllangoK/master
...
Fixes various button overflowing UI and compact checkbox
2023-01-23 15:22:06 +03:00
74608300d1
Merge pull request #7093 from Shondoit/fix-dark-mode
...
Fix dark mode
2023-01-23 15:09:26 +03:00
41265a026d
third time's the charm
2023-01-23 14:50:20 +03:00
fabdae089e
add missing import to previous commit
2023-01-23 14:42:49 +03:00
669dbd9725
Fix dark mode
...
Fixes #7048
Co-Authored-By: J.J. Tolton <jjtolton@gmail.com>
2023-01-23 09:54:42 +01:00
b5230197a6
rework extras tab to use script system
2023-01-23 09:24:43 +03:00
f80ff3c1e4
feat(extra-networks): remove view dropdown
2023-01-22 22:01:24 -03:00
66eef11ce7
feat(extra-networks): add default view setting
2023-01-22 12:18:21 -03:00
985c0b8e9a
feat(extra-networks): add thumbs view style
2023-01-22 12:18:21 -03:00
3bc8ee998d
Gen params paste improvement
2023-01-22 16:35:42 +03:00
7f62300f7d
Gen params paste improvement
2023-01-22 16:29:08 +03:00
fccc39834a
Gen params paste improvement
2023-01-22 16:17:55 +03:00
d261bec1ec
Gen params paste improvement
2023-01-22 16:14:28 +03:00
1fa777c1d7
Gen params paste improvement
2023-01-22 16:03:42 +03:00
2aaee73633
Gen params paste improvement
2023-01-22 16:00:35 +03:00
a5c2b5ed89
UI and PNG info improvements
2023-01-22 15:50:20 +03:00
bbb1e35ea2
UI and PNG info improvements
2023-01-22 15:44:59 +03:00
b0ae92d605
UI improvements
2023-01-22 15:43:12 +03:00
68303c96e5
split oversize extras.py to postprocessing.py
2023-01-22 15:38:39 +03:00
34f6d66742
hr conditioning
2023-01-22 15:32:47 +03:00
125d5c8d96
hr conditioning
2023-01-22 15:31:11 +03:00
2ab2bce74d
hr conditioning
2023-01-22 15:28:38 +03:00
c56b367122
Split history extras.py to postprocessing.py
2023-01-22 15:26:41 +03:00
d63340a485
Split history extras.py to postprocessing.py
2023-01-22 15:26:40 +03:00
b238b14ee4
Split history extras.py to postprocessing.py
2023-01-22 15:26:40 +03:00
43ac9ff205
Split history extras.py to postprocessing.py
2023-01-22 15:26:40 +03:00
c5d4c87c02
hr conditioning
2023-01-22 15:17:43 +03:00
4e0cf7d4ed
hr conditioning
2023-01-22 15:15:08 +03:00
a9f0e7d536
hr conditioning
2023-01-22 15:12:00 +03:00
f774a8d24e
Hr-fix separate prompt experimentation
2023-01-22 14:52:01 +03:00
81e0723d65
Logging for debugging
2023-01-22 14:41:41 +03:00
b331ca784a
Fix
2023-01-22 14:35:34 +03:00
8114959e7e
Hr separate prompt test
2023-01-22 14:28:53 +03:00
c98cb0f8ec
amend previous commit to work in a proper fashion when saving previews
2023-01-22 11:04:02 +03:00
35419b2746
add an option to reorder tabs for extra networks
2023-01-22 11:00:05 +03:00
112416d041
add option to discard weights in checkpoint merger UI
2023-01-22 10:17:12 +03:00
0792fae078
fix missing field for aesthetic embedding extension
2023-01-22 08:20:48 +03:00
2621566153
attention ctrl+up/down enhancements
2023-01-22 08:07:18 +03:00
bf457b30fb
compact checkbox and fix copy image btn overflow
...
also fixes type for #tab_extensions in style.css
2023-01-21 16:21:33 -05:00
f7b38c4841
Style fix
2023-01-22 00:18:26 +03:00
f2eae6127d
fix broken textual inversion extras tab
2023-01-22 00:16:26 +03:00
0f6862ef30
PLMS edge-case handling fix 5
2023-01-22 00:11:05 +03:00
6cd7bf9f86
PLMS edge-case handling fix 3
2023-01-22 00:08:58 +03:00
3ffe2e768b
PLMS edge-case handling fix 2
2023-01-22 00:07:46 +03:00
9e1f49c4e5
PLMS edge-case handling fix
2023-01-22 00:03:16 +03:00
fe7a623e6b
add a slider for default value of added extra networks
2023-01-22 00:02:52 +03:00
78f59a4e01
enable compact view for train tab
...
prevent previews from ruining hypernetwork training
2023-01-22 00:02:51 +03:00
8bec3a2aa1
Index fix
2023-01-21 23:31:36 +03:00
6c0566f937
Type mismatch fix
2023-01-21 23:25:36 +03:00
abf11215e0
Merge pull request #6955 from EllangoK/master
...
Adds descriptions for merging methods in UI
2023-01-21 23:17:06 +03:00
3bd898b6ce
First test of different sampler for hi-res fix
2023-01-21 23:14:59 +03:00
4a8fe09652
remove the double loading text
2023-01-21 23:06:18 +03:00
e4e0918f58
remove timestamp for js files, reformat code
2023-01-21 22:57:19 +03:00
7c8852b8e7
Merge pull request #7015 from jjtolton/serve-static-js
...
Compile and serve js files via `src` instead of embedded inline scripts
2023-01-21 22:43:18 +03:00
035459c9a2
remove dead import
2023-01-21 14:11:13 -05:00
50059ea661
server individually listed javascript files vs single compiled file
2023-01-21 14:07:48 -05:00
17af0fb955
remove commented out lines
2023-01-21 13:27:05 -05:00
f726df8a2f
Compile and serve js from /statica instead of inline in html
2023-01-21 12:59:05 -05:00
f53527f778
make it run on gradio < 3.16.2
2023-01-21 20:07:14 +03:00
3deea34135
extract extra network data from prompt earlier
2023-01-21 19:36:08 +03:00
63b824376c
add --gradio-queue option to enable gradio queue
2023-01-21 18:47:54 +03:00
424cefe118
add search box to extra networks
2023-01-21 17:20:24 +03:00
92fb1096db
make it so that extra networks are not removed from infotext
2023-01-21 16:41:25 +03:00
855b9e3d1c
Lora support!
...
update readme to reflect some recent changes
2023-01-21 16:15:53 +03:00
3262e825cc
add --xformers-flash-attention option & impl
2023-01-21 17:42:04 +09:00
184e23eb89
relocate tool buttons next to generate button
...
prevent extra network tabs from putting images into wrong prompts
prevent settings leaking into prompt
2023-01-21 09:58:57 +03:00
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
2023-01-21 09:14:27 +03:00
40ff6db532
extra networks UI
...
rework of hypernets: rather than via settings, hypernets are added directly to prompt as <hypernet:name:weight>
2023-01-21 08:36:07 +03:00
20a59ab3b1
move token counter to the location of the prompt, add token counting for the negative prompt
2023-01-20 10:18:41 +03:00
98466da4bc
adds descriptions for merging methods in ui
2023-01-20 00:48:15 -05:00
6c7a50d783
remove some unnecessary logging to javascript console
2023-01-20 08:36:37 +03:00
6073456c83
write a comment for fix_checkpoint function
2023-01-19 20:39:10 +03:00
51517f3ea6
Merge pull request #6936 from EllangoK/master
...
Fixes minor typos around run_modelmerger
2023-01-19 19:58:16 +03:00
c1928cdd61
bring back short hashes to sd checkpoint selection
2023-01-19 18:58:08 +03:00
f2ae252987
fixes minor typos around run_modelmerger
2023-01-19 10:24:17 -05:00
d1ea518dea
remember the list of checkpoints after you press refresh button and reload the page
2023-01-19 18:07:37 +03:00
b271e22f7a
Update shared.py
...
`Witdth/Height` was driving me insane. -> `Width/Height`
2023-01-19 06:12:19 -05:00
aa60fc6660
Merge pull request #6922 from brkirch/cumsum-fix
...
Improve cumsum fix for MPS
2023-01-19 13:18:34 +03:00
0f9cacaa0e
Merge pull request #6844 from guaneec/crop-ui
...
Add auto-sized cropping UI
2023-01-19 13:11:05 +03:00
2985b317d7
Fix of fix
2023-01-19 17:39:30 +08:00
18a09c7e00
Simplification and bugfix
2023-01-19 17:36:23 +08:00
54674674b8
allow having at half precision when there is only one checkpoint in merger tab
2023-01-19 12:12:09 +03:00
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
2023-01-19 10:39:51 +03:00
c7e50425f6
add progress bar to modelmerger
2023-01-19 09:25:37 +03:00
7cfc645030
eliminate repetition of code in #6910
2023-01-19 08:53:50 +03:00
01b1061a0b
Merge pull request #6910 from EllangoK/master
...
Check model name values are set before merging
2023-01-19 08:48:27 +03:00
308b51012a
fix an unlikely division by 0 error
2023-01-19 08:41:37 +03:00
26a6a78b16
only lookup tertiary model if theta_func1 is set
2023-01-18 21:21:52 -05:00
99207bc816
check model name values are set before merging
2023-01-18 19:13:15 -05:00
bb0978ecfd
fix hires fix ui weirdness caused by gradio update
2023-01-19 00:44:51 +03:00
a8322ad75b
Merge pull request #6854 from EllangoK/master
...
Saves Extra Generation Parameters to params.txt
2023-01-18 23:25:56 +03:00
43fd6eaab8
Merge pull request #6851 from ddPn08/master
...
Add `--vae-dir` argument
2023-01-18 23:23:09 +03:00
b186d44dcd
use DDIM in hires fix is the sampler is PLMS
2023-01-18 23:20:23 +03:00
c94abc8862
Merge pull request #6895 from mezotaken/interrogate-all-tabs
...
Process interrogation on all img2img subtabs
2023-01-18 23:07:41 +03:00
924e222004
add option to show/hide warnings
...
removed hiding warnings from LDSR
fixed/reworked few places that produced warnings
2023-01-18 23:04:24 +03:00
8683427bd9
Process interrogation on all img2img subtabs
2023-01-18 20:25:52 +03:00
6faae23239
repair broken quicksettings when some form-requiring options are added to it
2023-01-18 14:33:09 +03:00
26fd444811
bump gradio to 3.16.2
...
change style selection to multiselect dropdown
2023-01-18 13:59:45 +03:00
a255dac4f8
Fix cumsum for MPS in newer torch
...
The prior fix assumed that testing int16 was enough to determine if a fix is needed, but a recent fix for cumsum has int16 working but not bool.
2023-01-17 20:54:18 -05:00
d906f87043
fix typo
2023-01-18 07:52:10 +09:00
3a0d6b7729
make it so that PNG images with EXIF do not lose parameters in PNG info tab
2023-01-17 23:54:23 +03:00
5e15a0b422
Changed params.txt save to after manual init call
2023-01-17 11:42:44 -05:00
6e08da2c31
Add `--vae-dir` argument
2023-01-17 23:50:41 +09:00
aede265f1d
Fix unable to find Real-ESRGAN model info error (AttributeError: 'NoneType' object has no attribute 'data_path') #6841 #5170
2023-01-17 13:57:55 +03:00
4688bfff55
Add auto-sized cropping UI
2023-01-17 17:16:43 +08:00
c361b89026
disable the new NaN check for the CI
2023-01-17 11:05:01 +03:00
AUTOMATIC