9441c28c94
add an option for img2img background color
2022-12-24 09:46:35 +03:00
22f1527fa7
feat(api): add override_settings_restore_afterwards
2022-12-20 20:36:49 +11:00
c0355caefe
Fix various typos
2022-12-14 21:01:32 -05:00
7077428209
Save hypernetwork hash in infotext
2022-12-13 13:05:40 -08:00
2e8b5418e3
Improve color correction with luminosity blend
2022-12-11 18:03:36 -05:00
94a35ca9d6
Merge pull request #5191 from aliencaocao/enable_checkpoint_switching_in_override_settings
...
Support changing checkpoint and vae through override_settings
2022-12-10 16:29:40 +03:00
991e2dcee9
remove NSFW filter and its dependency; if you still want it, find it in the extensions section
2022-12-10 14:54:16 +03:00
bab91b1279
add Noise multiplier option to infotext
2022-12-10 09:51:26 +03:00
8ee1acc1e4
Merge pull request #5373 from mezotaken/master
...
add noise strength parameter similar to NAI
2022-12-10 09:36:24 +03:00
1ed4f0e228
Depth2img model support
2022-12-08 20:50:08 -06:00
358a8628f6
Add latent upscale option to img2img
...
Recently, the option to do latent upscale was added to txt2img highres
fix. This feature runs by scaling the latent sample of the image, and
then running a second pass of img2img.
But, in this edition of highres fix, the image and parameters cannot be
changed between the first pass and second pass. We might want to do a
fixup in img2img before doing the second pass, or might want to run the
second pass at a different resolution.
This change adds the option for img2img to perform its upscale in latent
space, rather than image space, giving very similar results to highres
fix with latent upscale. The result is not exactly the same because
there is an additional latent -> decoder -> image -> encoder -> latent
that won't happen in highres fix, but this conversion has relatively
small losses
2022-12-08 07:09:09 +00:00
cf3e844d1d
add noise strength parameter similar to NAI
2022-12-03 18:05:47 +03:00
d2e5b4edfa
Merge pull request #5251 from adieyal/bug/negative-prompt-infotext
...
Fixed incorrect negative prompt text in infotext
2022-12-03 10:21:43 +03:00
a44994e2c9
Fixed incorrect negative prompt text in infotext
...
Previously only the first negative prompt in all_negative_prompts was
being used for infotext. This fixes that by selecting the index-th
negative prompt
2022-11-30 15:23:53 +02:00
9a8678f61e
Support changing checkpoint and vae through override_settings
2022-11-29 11:11:29 +08:00
67efee33a6
Make VAE step sequential to prevent VRAM spikes
2022-11-28 16:29:43 +05:00
40ca34b837
fix for broken sampler selection in img2img and xy plot #4860 #4909
2022-11-27 13:17:39 +03:00
828438b4a1
Merge pull request #4120 from aliencaocao/enable-override-hypernet
...
Enable override_settings to take effect for hypernetworks
2022-11-20 16:49:06 +03:00
413c077969
prevent StableDiffusionProcessingImg2Img changing image_mask field as an alternative solution to #4765
2022-11-19 13:48:59 +03:00
617c5b486f
make it possible for StableDiffusionProcessing to accept multiple different negative prompts in a batch
2022-11-19 13:23:25 +03:00
e35d8b493f
Merge pull request #4778 from leppie/fix_unbounded_prompt_growth
...
Fix unbounded prompt growth/determinism in scripts that loop
2022-11-19 12:52:55 +03:00
0d702930b0
renamed Inpainting strength infotext to Conditional mask weight, made it only appear if using inpainting model, made it possible to read the setting from it using the blue arrow button
2022-11-19 12:47:52 +03:00
ff35ae9abb
Merge pull request #4679 from Eugenii10/inpaint-strength-to-infotext
...
Add 'Inpainting strength' to the 'generation_params' of 'infotext' (params.txt or png chunks)
2022-11-19 12:24:44 +03:00
cdc8020d13
change StableDiffusionProcessing to internally use sampler name instead of sampler index
2022-11-19 12:01:51 +03:00
9bbe1e3c2e
Fix unbounded prompt growth scripts that loop
2022-11-16 19:19:00 +02:00
40ae95d532
Fix retrieving value for 'x/y plot' script.
2022-11-14 18:05:59 +10:00
6fa891b934
Add 'Inpainting strength' to the 'generation_params' dictionary of 'infotext' which is saved into the 'params.txt' or png chunks.
...
Value appears only if 'Denoising strength' appears too.
2022-11-14 00:25:38 +10:00
c13e234444
Merge branch 'master' into enable-override-hypernet
2022-11-06 16:33:08 +08:00
55ca040958
Resolve conflict
2022-11-06 16:31:44 +08:00
eeb0733013
change process_one virtual function for script to process_batch, add extra args and docs
2022-11-04 11:21:40 +03:00
c250d2a08f
Merge pull request #4182 from macrosoft/process_one
...
Process one
2022-11-04 11:07:05 +03:00
f674c488d9
bugfix: save image for hires fix BEFORE upscaling latent space
2022-11-04 10:45:34 +03:00
f2b69709ea
move option access checking to options class out of various places scattered through code
2022-11-04 09:42:25 +03:00
243253ff4a
Merge branch 'AUTOMATIC1111:master' into master
2022-11-03 15:55:54 -07:00
de64146ad2
add number of itter
2022-11-02 21:30:50 +03:00
a9e979977a
process_one
2022-11-02 19:05:01 +03:00
eb5e82c7dd
do not unnecessarily run VAE one more time when saving intermediate image with hires fix
2022-11-02 12:45:03 +03:00
9c67408004
Allow saving "before-highres-fix. ( #4150 )
...
* Save image/s before doing highres fix.
2022-11-02 12:18:21 +03:00
c9148b2312
Release processing resources after it finishes
2022-11-01 21:56:47 -03:00
bc60768606
Enable override_settings to take effect for hypernetworks
2022-11-01 23:26:55 +08:00
af758e97fa
Unload sd_model before loading the other
2022-11-01 04:01:49 -03:00
71571e3f05
Replaced master branch fix with updated fix.
2022-10-30 00:35:40 -07:00
15468c9939
Merge branch 'AUTOMATIC1111:master' into master
2022-10-30 00:30:18 -07:00
61836bd544
shorten Hypernetwork strength in infotext and omit it when it's the default value.
2022-10-30 08:48:53 +03:00
470f184176
Merge pull request #3831 from timntorres/3825-save-hypernet-strength-to-info
...
Save Hypernetwork strength to infotext.
2022-10-30 08:47:18 +03:00
05a657dd35
fix broken hires fix
2022-10-30 07:41:56 +03:00
e709afb0f7
Merge commit 'e7254746bbfbff45099db44a8d4d25dd6181877d' into 3825-save-hypernet-strength-to-info
2022-10-29 14:55:30 -07:00
39f55c3c35
Re-add explicit device move
2022-10-29 14:13:02 -07:00
9bb6b6509a
add postprocess call for scripts
2022-10-29 22:20:02 +03:00
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.
2022-10-29 10:35:51 -07:00
44ab954fab
Fix latent upscale highres fix #3888
2022-10-29 10:02:56 -07:00
2c4d203884
Revert "Explicitly state when Hypernet is none."
2022-10-29 00:36:51 -07:00
e98f72be33
Merge branch 'AUTOMATIC1111:master' into 3825-save-hypernet-strength-to-info
2022-10-29 00:31:23 -07:00
c0677b3316
Explicitly state when Hypernet is none.
2022-10-27 23:31:45 -07:00
9e465c8aa5
Add strength to textinfo.
2022-10-27 23:03:34 -07:00
26a3fd2fe9
Highres fix works with unmasked latent.
...
Also refactor the mask creation to make it more accesible.
2022-10-27 11:27:59 -07:00
f3f2ffd448
Merge branch 'AUTOMATIC1111:master' into master
2022-10-27 11:19:12 -07:00
1e428238db
add override_settings to API as an alternative to #3629
2022-10-26 11:47:17 +03:00
8b4f32779f
Switch to a continous blend for cond. image.
2022-10-25 13:15:08 -07:00
605d27687f
Added conditioning image masking to xy_grid.
...
Use `True` and `False` to select values.
2022-10-25 12:20:54 -07:00
f9549d1cbb
Added option to use unmasked conditioning image.
2022-10-25 11:14:12 -07:00
6cbb04f7a5
fix #3517 breaking txt2img
2022-10-24 09:15:26 +03:00
f2cc3f32d5
fix whitespaces
2022-10-24 08:58:56 +03:00
9741969325
Save properly processed image before color correction
2022-10-24 08:58:56 +03:00
9e1a8b7734
non-implemented mask with any type
2022-10-23 09:26:56 +03:00
a7c213d0f5
[API][Feature] - Add img2img API endpoint
2022-10-23 09:26:56 +03:00
ca5a9e79dc
fix for img2img color correction in a batch #3218
2022-10-22 22:06:54 +03:00
324c7c732d
record First pass size as 0x0 for #3328
2022-10-22 20:09:51 +03:00
2b91251637
removed aesthetic gradients as built-in
...
added support for extensions
2022-10-22 12:23:58 +03:00
fccad18a59
Refer to Hypernet's name, sensibly, by its name variable.
2022-10-21 16:52:24 +03:00
df57064093
do not load aesthetic clip model until it's needed
...
add refresh button for aesthetic embeddings
add aesthetic params to images' infotext
2022-10-21 16:10:51 +03:00
bf30673f51
Fix Hypernet infotext string split bug for PR #3283
2022-10-21 10:19:25 +03:00
4587218190
updated readme and some small stylistic changes to code
2022-10-21 09:00:39 +03:00
92a17a7a4a
Made dummy latents smaller. Minor code cleanups
2022-10-20 09:45:03 -07:00
aa7ff2a197
Fixed non-square highres fix generation
2022-10-19 21:46:13 -07:00
c418467c03
Don't compute latent mask if were not using it. Also added support for fixed highres_fix generation.
2022-10-19 15:09:43 -07:00
8e7097d06a
Added support for RunwayML inpainting model
2022-10-19 13:47:45 -07:00
5e012e4dfa
Infotext saves more specific hypernet name.
2022-10-19 20:20:25 +03:00
5daf9cbb98
Merge remote-tracking branch 'origin/api'
2022-10-19 08:44:51 +03:00
cbf15edbf9
remove dependence on TQDM for sampler progress/interrupt functionality
2022-10-18 17:23:38 +03:00
f80e914ac4
example API working with gradio
2022-10-17 19:10:36 +00:00
60251c9456
initial prototype by borrowing contracts
2022-10-17 11:34:22 +03:00
c9836279f5
Only make output dir when creating output
2022-10-16 16:36:06 +03:00
0c5fa9a681
do not reload embeddings from disk when doing textual inversion
2022-10-16 09:09:04 +03:00
97f0727489
add First pass size always regardless of whether it was auto chosen or specified
2022-10-15 15:47:02 +03:00
f7ca63937a
bring back scale latent option in settings
2022-10-15 13:23:12 +03:00
a13af34b90
Set to -1 when seed input is none
2022-10-15 10:12:16 +03:00
368f4cc4c7
set firstpass w/h to 0 by default and rever to old behavior when any are 0
2022-10-14 23:19:05 +03:00
e644b5a80b
remove scale latent and no-crop options from hires fix
...
support copy-pasting new parameters for hires fix
2022-10-14 17:03:03 +03:00
b382de2d77
Fixed Scale ratio problem
2022-10-14 16:47:16 +03:00
40d1c6e423
Option between stretch and crop for Highres. fix
2022-10-14 16:47:16 +03:00
b2261b53ae
Added first_pass_width and height as adjustable inputs to "High Res Fix"
2022-10-14 16:47:16 +03:00
e72adc999b
Restore last generation params
2022-10-13 12:21:20 +03:00
39919c40dd
add eta noise seed delta option
2022-10-10 20:32:44 +03:00
8f1efdc130
--no-half-vae pt2
2022-10-10 17:03:45 +03:00
7349088d32
--no-half-vae
2022-10-10 16:16:29 +03:00
8d340cfb88
do not add clip skip to parameters if it's 1 or 0
2022-10-09 22:31:35 +03:00
ec2bd9be75
Fix issues with CLIP ignore option name change
2022-10-09 22:31:23 +03:00
e6e8cabe0c
change up #2056 to make it work how i want it to plus make xy plot write correct values to images
2022-10-09 14:57:48 +03:00
594cbfd8fb
Sanitize infotext output (for now)
2022-10-09 14:49:15 +03:00
006791c13d
Fix grabbing the model name for infotext
2022-10-09 14:49:15 +03:00
d6d10a37bf
Added extended model details to infotext
2022-10-09 14:49:15 +03:00
bd833409ac
additional changes for saving pnginfo for #1803
2022-10-09 13:10:15 +03:00
ef93acdc73
remove line break
2022-10-09 11:09:17 +03:00
03e570886f
Fix incorrect sampler name in output
2022-10-09 11:09:17 +03:00
050a6a798c
support loading .yaml config with same name as model
...
support EMA weights in processing (????)
2022-10-08 23:26:48 +03:00
432782163a
chore: Fix typos
2022-10-08 22:42:30 +03:00
3b2141c5fb
add 'Ignore last layers of CLIP model' option as a parameter to the infotext
2022-10-08 22:21:15 +03:00
5f85a74b00
fix bug where when using prompt composition, hijack_comments generated before the final AND will be dropped
2022-10-08 15:48:04 +03:00
4999eb2ef9
do not let user choose his own prompt token count limit
2022-10-08 14:25:47 +03:00
00117a07ef
check specifically for skipped
2022-10-08 13:40:39 +03:00
786d9f63aa
Add button to skip the current iteration
2022-10-08 13:40:39 +03:00
706d5944a0
let user choose his own prompt token count limit
2022-10-08 13:38:57 +03:00
1cc36d170a
Added job_timestamp to Processed
...
So `[job_timestamp]` pattern can use in saving image UI.
2022-10-06 20:41:23 +03:00
070b7d60cf
Added styles to Processed
...
So `[styles]` pattern can use in saving image UI.
2022-10-06 20:41:23 +03:00
dbc8a4d351
add generation parameters to images shown in web ui
2022-10-06 20:27:50 +03:00
b66aa334a9
Merge branch 'master' into fix-vram
2022-10-06 13:41:37 -03:00
5993df24a1
integrate the new samplers PR
2022-10-06 14:12:52 +03:00
5f24b7bcf4
option to let users select which samplers they want to hide
2022-10-06 12:08:59 +03:00
c26732fbee
added support for AND from https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/
2022-10-05 23:16:27 +03:00
82380d9ac1
Removing parts no longer needed to fix vram
2022-10-04 22:31:40 -03:00
1f50971fb8
Merge branch 'master' into fix-vram
2022-10-04 19:53:52 -03:00
90e911fd54
prompt_parser: allow spaces in schedules, add test, log/ignore errors
...
Only build the parser once (at import time) instead of for each step.
doctest is run by simply executing modules/prompt_parser.py
2022-10-04 20:26:15 +03:00
e1b128d8e4
do not touch p.seed/p.subseed during processing #1181
2022-10-04 17:36:39 +03:00
52cef36f6b
emergency fix for img2img
2022-10-04 16:54:31 +03:00
6165246124
support interrupting after the previous change
2022-10-04 14:23:22 +03:00
6c6ae28bf5
send all three of GFPGAN's and codeformer's models to CPU memory instead of just one for #1283
2022-10-04 12:32:22 +03:00
ad0cc85d1f
Merge branch 'master' into stable
2022-10-02 18:31:19 -03:00
5f561ee95d
Merge remote-tracking branch 'origin/master'
2022-10-02 15:49:59 +03:00
820f1dc96b
initial support for training textual inversion
2022-10-02 15:03:39 +03:00
9de1e56e2d
add sampler_noise_scheduler_override property
2022-10-01 08:08:50 +03:00
ad1fbbae93
Merge branch 'master' into fix-vram
2022-09-30 18:58:51 -03:00
9a54077d4d
repair broken highres fix #1109
2022-09-30 12:26:41 +03:00
c938679de7
Fix memory leak and reduce memory usage
2022-09-28 22:14:13 -03:00
1deac2b645
do nor add log messages to saved iamge parameters
2022-09-28 18:20:30 +03:00
d64b451681
added support for automatically installing latest k-diffusion
...
added eta parameter to parameters output for generated images
split eta settings into ancestral and ddim (because they have different default values)
2022-09-28 18:09:06 +03:00
aea5b2510e
save parameters for images when using the Save button.
2022-09-28 17:05:23 +03:00
5391c0bf3e
Update processing.py
2022-09-28 05:11:03 +03:00
4ea36a37d6
add sampler properties to StableDiffusionProcessing and Processed
2022-09-27 09:30:45 +03:00
8dcac9ac81
Grids saving to subdirectory when setting unchecked
...
Fixed grids saving to subdirectory when the setting is unchecked but "save images to subdirectory" was checked.
2022-09-27 08:58:47 +03:00
31ac0baba0
Reformat some changes from the previous commit.
2022-09-24 08:23:01 +03:00
ed8b8b3b8c
Fix to XY_Grid script console progress bar and other progress bar improvements ( #890 )
...
Fix to XY_Grid script console progress bar and other progress bar improvements #890
2022-09-24 08:09:59 +03:00
0f77e1852f
Clear no longer needed VRAM during a 'highres fix' generation created during the first sampling before doing the second (img2img) sampling. Makes it possible to use the feature on an 8GB card.
2022-09-24 07:41:59 +03:00
1a0353675d
Option to use advanced upscalers with normal img2img
2022-09-23 17:37:47 +03:00
d26d89377b
Remove unnecessary duplication
2022-09-23 00:57:42 +00:00
25eb1e3d90
Add option to save before color correction. Add suffix param when saving files, used for special saves without color correction and face restoration.
2022-09-22 20:54:50 +10:00
91bfc71261
A big rework, just what you were secretly hoping for!
...
SD upscale moved to scripts
Batch processing script removed
Batch processing added to main img2img and now works with scripts
img2img page UI reworked to use tabs
2022-09-22 12:11:48 +03:00
75dd274dd6
prevent seed extras from having effect when extras checkbox is not checked
2022-09-21 13:34:10 +03:00
19a75d38d7
added --use-textbox-seed option to make long seeds possible from web ui
2022-09-20 20:10:01 +03:00
06cd206107
Enable neural network upscalers for highres. fix
2022-09-20 19:32:26 +03:00
b9674e2900
add extra generation params
2022-09-20 19:07:09 +03:00
6d7ca54a1a
added highres fix feature
2022-09-19 16:42:56 +03:00
7539f04e28
made 'reuse seed' button give you the seed/subseed of the currently selected picture rather than the first
2022-09-19 09:02:10 +03:00
21086e60a9
Merge remote-tracking branch 'origin/master'
2022-09-18 20:55:55 +03:00
6a28aac866
prevent black screen when seed and variation seed are the same.
2022-09-18 20:44:57 +03:00
4c17ce4949
handle NoneType when subseed is not initialized. Set it to -1 in that case
2022-09-18 09:57:50 -07:00
c76a616bc9
fix many paths in code breaking because Processing constructor changed
2022-09-18 19:03:37 +03:00
a96076f49c
Add buttons for random and reuse seed.
...
Random button sets seed to -1, reuse copies the seed from the last
generated image.
2022-09-18 15:13:28 +02:00
b273458d2d
make inpaint at full resolution option not discard useful pixels from the image
...
split masking helper function from processing.py into new masking.py
2022-09-18 10:49:00 +03:00
f39b2ca088
fixed typos in processing.py
2022-09-17 22:09:52 -07:00
7bc5739fe2
set loopback color corrections on each iteration
2022-09-17 18:18:30 -04:00
ba295b3268
* Fix process_images where the number of images is not a multiple of (batch_size * n_iter), which would cause us to throw an exception.
...
* Add a textbox option to Prompts from file (ease of use and it makes it much easier to use on a mobile device)
* Fix the fact that Prompts from file was sometimes passing an empty batch.
2022-09-17 14:55:54 +03:00
247f58a5e7
add support for switching model checkpoints at runtime
2022-09-17 12:05:18 +03:00
b8cf2ea8ea
add a bit of a comment about what's being done with tensor noise
2022-09-16 10:04:07 +03:00
83bce1a604
Merge branch 'batch-seed-attempt'
2022-09-16 09:48:46 +03:00
87e8b9a2ab
prevent replacing torch_randn globally (instead replacing k_diffusion.sampling.torch) and add a setting to disable this all
2022-09-16 09:47:03 +03:00
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
2022-09-16 08:33:47 +03:00
f2693bec08
prompt editing
2022-09-15 13:10:16 +03:00
b28cf84c36
prevent repeating messages about too many tokens
2022-09-15 08:57:03 +03:00
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
2022-09-14 17:56:21 +03:00
6bea45d495
prevent making grid if there is no need for it #428
2022-09-14 10:34:44 +03:00
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
2022-09-14 08:58:13 +03:00
9d40212485
first attempt to produce crrect seeds in batch
2022-09-13 21:49:58 +03:00
7a5852a4ee
change np.float to np.float32
...
* numpy deprecation warning fix. Alternately, you could also specify float
2022-09-13 18:21:59 +03:00
c84e333622
color correction option for all img2img modes #363
2022-09-13 12:51:57 +03:00
b5a8b99d3f
put safety checker into a separate file because it's already crowded in processing
2022-09-13 08:34:41 +03:00
fc18e2d483
Adds NSFW content filter option
2022-09-12 19:15:35 -05:00
19a817d97d
X/Y plot with denoising adds incorrect image data to individual outputs #331
2022-09-12 23:44:36 +03:00
3de44fc580
Include the model name (or the SHA256 of the file) in the metadata #271
2022-09-12 20:47:46 +03:00
c7e0e28ccd
changes for #294
2022-09-12 20:09:32 +03:00
11e03b9abd
Merge pull request #294 from EliasOenal/master
...
Fixes for mps/Metal: use of seeds, img2img, CodeFormer
2022-09-12 19:58:06 +03:00
a655e90fbe
add negative prompt to log when clicking save #249
2022-09-12 19:57:31 +03:00
40f4d3ed98
[FEATURE] Save both images, (Skip_Save optional). #265
2022-09-12 17:47:36 +03:00
b7f95869b4
Refactored Metal/mps fixes.
2022-09-12 16:32:44 +02:00
a1305060ce
Variations are not working properly #305
2022-09-12 16:00:46 +03:00
a4416f3585
[BUG] Not Working As Intended - create a directory with name derived from the prompt #306
2022-09-12 15:41:30 +03:00
81d91cea29
Merge remote-tracking branch 'origin/master'
2022-09-11 23:25:35 +03:00
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.
2022-09-11 23:25:20 +03:00
8fb9c57ed6
add half() supporrt for CLIP interrogation
2022-09-11 23:24:24 +03:00
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.
2022-09-11 21:11:02 +02:00
13008bab90
Fixed prompt_style type hints: int -> str
2022-09-11 12:39:09 +03:00
b3311a50dc
fix repeating subseeds for every batch #221
2022-09-10 16:16:18 +03:00
fbdec2ef20
Fix prompt matrix script
2022-09-09 23:40:03 +03:00
86867e153f
support for prompt styles
...
fix broken prompt matrix
2022-09-09 23:16:02 +03:00
5b6a585ae5
Merge remote-tracking branch 'origin/master' into seeds
2022-09-09 19:13:40 +03:00
17a7477c72
Include negative prompt in parameters text file
2022-09-09 18:19:37 +03:00
b1707553cf
added resize seeds and variation seeds features
2022-09-09 17:54:04 +03:00
0fedd50886
another change for inpainting at full resolution
2022-09-08 10:03:21 +03:00
700c47a674
big improvements to inpainting and outpainting
2022-09-07 17:00:51 +03:00
6a9b33c848
codeformer support
2022-09-07 12:32:28 +03:00
AUTOMATIC