b186d44dcd
use DDIM in hires fix is the sampler is PLMS
3 years ago
c94abc8862
Merge pull request #6895 from mezotaken/interrogate-all-tabs
...
Process interrogation on all img2img subtabs
3 years ago
924e222004
add option to show/hide warnings
...
removed hiding warnings from LDSR
fixed/reworked few places that produced warnings
3 years ago
8683427bd9
Process interrogation on all img2img subtabs
3 years ago
6faae23239
repair broken quicksettings when some form-requiring options are added to it
3 years ago
26fd444811
bump gradio to 3.16.2
...
change style selection to multiselect dropdown
3 years ago
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.
3 years ago
d906f87043
fix typo
3 years ago
3a0d6b7729
make it so that PNG images with EXIF do not lose parameters in PNG info tab
3 years ago
5e15a0b422
Changed params.txt save to after manual init call
3 years ago
6e08da2c31
Add `--vae-dir` argument
3 years ago
aede265f1d
Fix unable to find Real-ESRGAN model info error (AttributeError: 'NoneType' object has no attribute 'data_path') #6841 #5170
3 years ago
4688bfff55
Add auto-sized cropping UI
3 years ago
c361b89026
disable the new NaN check for the CI
3 years ago
eb2223340c
Fix typo
3 years ago
e0e8005009
make StableDiffusionProcessing class not hold a reference to shared.sd_model object
3 years ago
9991967f40
Add a check and explanation for tensor with all NaNs.
3 years ago
064983c0ad
return an option to hide progressbar
3 years ago
ff6a5bcec1
bugfix for previous commit
3 years ago
3f887f7f61
support old configs that say "auto" for ssd_vae
...
change sd_vae_as_default to True by default as it's a more sensible setting
3 years ago
3db22e6ee4
rename masking to inpaint in UI
...
make inpaint go to the right place for users who don't have it in config string
3 years ago
30cfe4ed9b
Merge pull request #6758 from Poktay/allow_reorder_masking_controls
...
allow reordering of inpaint masking controls (like the other sections can be reordered)
3 years ago
89314e79da
fix an error that happens when you send an empty image from txt2img to img2img
3 years ago
f3167b10ce
Merge pull request #6780 from vladmandic/train-logging
...
add fields to settings file
3 years ago
d6fa8e92ca
Merge pull request #6782 from aria1th/fix-hypernetwork-loss
...
Fix tensorboard-hypernetwork integration correctly
3 years ago
4385449933
Merge pull request #6778 from pangbo13/master
...
Fix unexpected behavior when show_progress_every_n_steps is set to -1
3 years ago
8e2aeee4a1
add BREAK keyword to end current text chunk and start the next
3 years ago
13445738d9
Fix tensorboard related functions
3 years ago
598f7fcd84
Fix loss_dict problem
3 years ago
110d1a2d59
add fields to settings file
3 years ago
205991df78
Merge remote-tracking branch 'origin/fix-mean-loss'
3 years ago
b6ce041cdf
put interrupt and skip buttons back where they were
3 years ago
a534bdfc80
add setting for progressbar update period
3 years ago
16f410893e
fix missing 'mean loss' for tensorboard integration
3 years ago
388708f7b1
fix when show_progress_every_n_steps == -1
3 years ago
ce13ced5dc
Merge pull request #6772 from vladmandic/sha-calc-optimization
...
increase block size
3 years ago
006997d180
Merge pull request #6770 from brkirch/approx-nn-fix
...
Fix Approx NN not working on torch devices other than CUDA
3 years ago
d8b90ac121
big rework of progressbar/preview system to allow multiple users to prompts at the same time and do not get previews of each other
3 years ago
f0312565e5
increase block size
3 years ago
eef1990a5e
Fix Approx NN on devices other than CUDA
3 years ago
9ef41df6f9
add inpaint masking controls to orderable section that the settings can order
3 years ago
ce9827a7c5
Merge pull request #6731 from vladmandic/state_server_start
...
Add server start time to state info
3 years ago
beeec2b598
Merge pull request #6728 from bbc-mc/exclude_clip_index_from_merge_target
...
Exclude clip index from merge
3 years ago
86359535d6
add buttons to copy images between img2img tabs
3 years ago
f8c5124785
typo?
3 years ago
a5bbcd2153
fix bug with "Ignore selected VAE for..." option completely disabling VAE election
...
rework VAE resolving code to be more simple
3 years ago
fad850fc3d
add server_start to shared.state
3 years ago
f94a215abe
add an option to choose what you want to see in live preview (Live preview subject) and moves live preview settings to its own tab
3 years ago
08c6f009a5
load hashes from cache for checkpoints that have them
...
add checkpoint hash to footer
3 years ago
865228a837
change style dropdowns to multiselect
3 years ago
5f8685237e
Exclude clip index from merge
3 years ago
6eb72fd13f
bump gradio to 3.16.1
3 years ago
febd2b722e
update key to use with checkpoints' sha256 in cache
3 years ago
f9ac3352cb
change hypernets to use sha256 hashes
3 years ago
a95f135308
change hash to sha256
3 years ago
82725f0ac4
fix a bug caused by merge
3 years ago
9cd7716753
Merge branch 'master' into tensorboard
3 years ago
544e7a233e
Merge pull request #6689 from Poktay/add_gradient_settings_to_logging_file
...
add gradient settings to training settings log files
3 years ago
3ad1fdd99b
Merge pull request #6684 from space-nuko/save-extension-params-to-last-params
...
Fix extension parameters not being saved to last used parameters
3 years ago
7bf3cfc427
Merge pull request #6685 from space-nuko/script-callback-fix-infotext
...
Add script callback for fixing infotext parameters
3 years ago
a176d89487
print bucket sizes for training without resizing images #6620
...
fix an error when generating a picture with embedding in it
3 years ago
486bda9b33
Merge pull request #6620 from guaneec/varsize_batch
...
Enable batch_size>1 for mixed-sized training
3 years ago
0b262802b8
add gradient settings to training settings log files
3 years ago
6c88eaed4f
Add script callback for fixing infotext parameters
3 years ago
88416ab5ff
Fix extension parameters not being saved to last used parameters
3 years ago
d52a80f7f7
Allow creation of zero vectors for TI
3 years ago
0b8911d883
img2img UI rework: obsolete --gradio-img2img-tool --gradio-inpaint-tool and always show all tools each in own tab
3 years ago
590ff5ce5b
Merge pull request #6647 from vladmandic/update-progress-api
...
add textinfo to progress api response
3 years ago
6d7f3d1072
Merge pull request #6648 from vladmandic/progress-description
...
Set TQDM progress bar and state textinfo description
3 years ago
97ff69eff3
Merge pull request #6628 from catboxanon/fix/alternating-words-emphasis
...
Fix prompt parser default step transformer
3 years ago
4bd490727e
fix for an error caused by skipping initialization, for realsies this time: TypeError: expected str, bytes or os.PathLike object, not NoneType
3 years ago
3f43d8a966
set descriptions
3 years ago
39ea251945
add textinfo to progress response
3 years ago
0b38b72d31
Remove compat option for prompt parser
3 years ago
ab388d6f8b
Remove compat option check for prompt parser
3 years ago
035f2af050
Merge branch 'AUTOMATIC1111:master' into fix/alternating-words-emphasis
3 years ago
1a23dc32ac
possible fix for fallback for fast model creation from config, attempt 2
3 years ago
4fdacd31e4
possible fix for fallback for fast model creation from config
3 years ago
954091697f
add an option to copy config from one of models in checkpoint merger
3 years ago
3e20244b0f
Merge pull request #6625 from PlasmaPower/textual-inversion-safetensors
...
Support loading textual inversion embeddings from safetensors files
3 years ago
37a2301121
Expose the compiled class module of scripts to extensions
3 years ago
7e45fba55b
Fix prompt parser default step transformer w/ test
3 years ago
5830095b73
Add old prompt parser compat option
3 years ago
f9706acf43
Support loading textual inversion embeddings from safetensors files
3 years ago
6be644fa04
Enable batch_size>1 for mixed-sized training
3 years ago
29fb532764
change color selector in settings to be part of form
3 years ago
0f8603a559
add support for transformers==4.25.1
...
add fallback for when quick model creation fails
3 years ago
ce3f639ec8
add more stuff to ignore when creating model from config
...
prevent .vae.safetensors files from being listed as stable diffusion models
3 years ago
0c3feb202c
disable torch weight initialization and CLIP downloading/reading checkpoint to speedup creating sd model from config
3 years ago
ef75c98053
Split history ui.py to ui_progress.py
3 years ago
54dd5d6634
Split history ui.py to ui_progress.py
3 years ago
f9c2147dfb
Split history ui.py to ui_progress.py
3 years ago
27ea6949d3
Split history ui.py to ui_progress.py
3 years ago
e9f8292a3a
Split history ui.py to ui_progress.py
3 years ago
a4a5475cfa
Variable dropout rate
...
Implements variable dropout rate from #4549
Fixes hypernetwork multiplier being able to modified during training, also fixes user-errors by setting multiplier value to lower values for training.
Changes function name to match torch.nn.module standard
Fixes RNG reset issue when generating previews by restoring RNG state
3 years ago
bd4587d2f5
Merge pull request #6578 from vladmandic/fix-model-load
...
allow model load if previous model failed
3 years ago
2275f130bf
relax reponse type check enforcement
3 years ago
552d7b90bf
allow model load if previous model failed
3 years ago
3fe9e9e54d
fix broken resolution detection when pasting parameters with old hires fix enabled
3 years ago
b1d976dca2
Merge pull request #6466 from vladmandic/api-get-memory
...
Implement API get-memory
3 years ago
95727312ca
remove bytes -> gb conversion
3 years ago
1fbb6f9ebe
make a dropdown for prompt template selection
3 years ago
43bb5190fc
remove/simplify some changes from #6481
3 years ago
18c001792a
Merge branch 'master' into varsize
3 years ago
cdfcbd9959
Remove fallback for Protocol import and remove Protocol import and remove instances of Protocol in code
...
add some whitespace between functions to be in line with other code in the repo
3 years ago
89c3663080
Merge pull request #6482 from ProGamerGov/patch-6
...
Add fallback for Protocol import
3 years ago
49c4509ce2
use existing function for loading VAE weights from file
3 years ago
99da2c5af6
Merge pull request #6528 from PlasmaPower/vae-safetensors
...
Add support for loading VAEs from safetensors files
3 years ago
d4fd2418ef
add an option to use old hiresfix width/height behavior
...
add a visual effect to inactive hires fix elements
3 years ago
cb255faec6
Add support for loading VAEs from safetensor files
3 years ago
0d194e4ecc
Merge pull request #6465 from brkirch/fix-training
...
Fix training for newer PyTorch builds
3 years ago
137ce534b2
remove some code duplication
...
remove calls to locals()
add a test for img2img with script
3 years ago
e7f2f1e1b6
Merge pull request #6469 from noodleanon/scripts-from-api
...
Run scripts from API
3 years ago
6d0cc1e239
Corrected is_img2img param
3 years ago
085427de0e
make it possible for extensions/scripts to add their own embedding directories
3 years ago
a0c87f1fdf
skip images in embeddings dir if they have a second .preview extension
3 years ago
984b86dd0a
Add fallback for Protocol import
3 years ago
72497895b9
Move batchsize check
3 years ago
669fb18d52
Add checkbox for variable training dims
3 years ago
448b9cedab
Allow variable img size
3 years ago
d38ede71d5
Added script support in txt2img endpoint
3 years ago
50e2536279
Merge branch 'AUTOMATIC1111:master' into img2img-api-scripts
3 years ago
47534577ed
api-get-memory
3 years ago
df3b31eb55
In-place operations can break gradient calculation
3 years ago
fdfce47110
add "from" resolution for hires fix to be less confusing.
3 years ago
983167e621
Merge pull request #6448 from aednzxy/patch-2
...
increase upscale api validation limit
3 years ago
c295e4a244
Merge pull request #6055 from brkirch/sub-quad_attn_opt
...
Add Birch-san's sub-quadratic attention implementation
3 years ago
1a5b86ad65
rework hires fix preview for #6437 : movie it to where it takes less place, make it actually account for all relevant sliders and calculate dimensions correctly
3 years ago
de97380445
this breaks on default config because width, height, hr_scale are None at that point.
3 years ago
01cc07b81a
Merge pull request #6437 from Mitchell1711/show-target-resolution
...
Show upscaled resolution on hires fix
3 years ago
c4a221c405
Merge branch 'clip_hijack_rework'
3 years ago
1740c33547
more comments
3 years ago
08066676a4
make it not break on empty inputs; thank you tarded, we are
3 years ago
f94cfc563b
Changed HTML to textbox instead
...
Using HTML caused an issue where the row would expand for a frame when changing the sliders because of the loading animation. This solution also doesn't use any additional HTML padding
3 years ago
79e39fae61
CLIP hijack rework
3 years ago
82c1f10b14
increase upscale api validation limit
3 years ago
c18add68ef
Added license
3 years ago
991368c8d5
remove camelcase
3 years ago
3992ecbe6e
Added UI elements
...
Added a new row to hires fix that shows the new resolution after scaling
3 years ago
50194de93f
typo UI fixes #6391
3 years ago
3246a2d6b8
remove restriction for saving dropdowns to ui-config.json
3 years ago
65ed4421e6
add callback for when the script is unloaded
3 years ago
c9bded39ee
sort extensions by date and add an option to sort by other columns
3 years ago
5deb2a19cc
Allow Doggettx's cross attention opt without CUDA
3 years ago
b95a4c0ce5
Change sub-quad chunk threshold to use percentage
3 years ago
683287d87f
rework saving training params to file #6372
3 years ago
b119815333
Use narrow instead of dynamic_slice
3 years ago
3bfe2bb549
Merge remote-tracking branch 'upstream/master' into sub-quad_attn_opt
3 years ago
f6ab5a39d7
Merge branch 'AUTOMATIC1111:master' into sub-quad_attn_opt
3 years ago
d782a95967
Add Birch-san's sub-quadratic attention implementation
3 years ago
AUTOMATIC
Vladimir Repin
brkirch
ddPn08
EllangoK
dan
fuggy
aria1th
Vladimir Mandic
pangbo13
Josh R
bbc_mc
space-nuko
Shondoit
catboxanon
Lee Bousfield
noodleanon
ProGamerGov
Mitchell Boot
Dean Hopkins
Kuma