invincibledude
c92ec3a925
Extra networks loading fix
2023-01-29 19:07:00 +03:00
InvincibleDude
ee3d63b6be
Merge branch 'master' into master
2023-01-29 14:36:10 +03:00
AUTOMATIC
00dab8f10d
remove Batch size and Batch pos from textinfo (goodbye)
2023-01-29 11:53:24 +03:00
AUTOMATIC1111
fecb990deb
Merge pull request #7309 from brkirch/fix-embeddings
...
Fix embeddings, upscalers, and refactor `--upcast-sampling`
2023-01-28 18:44:36 +03:00
brkirch
ada17dbd7c
Refactor conditional casting, fix upscalers
2023-01-28 04:16:25 -05:00
Max Audron
5eee2ac398
add data-dir flag and set all user data directories based on it
2023-01-27 14:44:30 +01:00
AUTOMATIC
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
brkirch
10421f93c3
Fix full previews, --no-half-vae
2023-01-26 01:43:35 -05:00
AUTOMATIC
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
AUTOMATIC1111
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
AUTOMATIC
57c1baa774
change to code for live preview fix on OSX to be bit more obvious
2023-01-25 18:56:23 +03:00
brkirch
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
brkirch
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
InvincibleDude
44c0e6b993
Merge branch 'AUTOMATIC1111:master' into master
2023-01-24 15:44:09 +03:00
brkirch
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
invincibledude
3bc8ee998d
Gen params paste improvement
2023-01-22 16:35:42 +03:00
invincibledude
7f62300f7d
Gen params paste improvement
2023-01-22 16:29:08 +03:00
invincibledude
a5c2b5ed89
UI and PNG info improvements
2023-01-22 15:50:20 +03:00
invincibledude
bbb1e35ea2
UI and PNG info improvements
2023-01-22 15:44:59 +03:00
invincibledude
34f6d66742
hr conditioning
2023-01-22 15:32:47 +03:00
invincibledude
125d5c8d96
hr conditioning
2023-01-22 15:31:11 +03:00
invincibledude
2ab2bce74d
hr conditioning
2023-01-22 15:28:38 +03:00
invincibledude
c5d4c87c02
hr conditioning
2023-01-22 15:17:43 +03:00
invincibledude
4e0cf7d4ed
hr conditioning
2023-01-22 15:15:08 +03:00
invincibledude
a9f0e7d536
hr conditioning
2023-01-22 15:12:00 +03:00
invincibledude
f774a8d24e
Hr-fix separate prompt experimentation
2023-01-22 14:52:01 +03:00
invincibledude
81e0723d65
Logging for debugging
2023-01-22 14:41:41 +03:00
invincibledude
b331ca784a
Fix
2023-01-22 14:35:34 +03:00
invincibledude
8114959e7e
Hr separate prompt test
2023-01-22 14:28:53 +03:00
invincibledude
0f6862ef30
PLMS edge-case handling fix 5
2023-01-22 00:11:05 +03:00
invincibledude
6cd7bf9f86
PLMS edge-case handling fix 3
2023-01-22 00:08:58 +03:00
invincibledude
3ffe2e768b
PLMS edge-case handling fix 2
2023-01-22 00:07:46 +03:00
invincibledude
9e1f49c4e5
PLMS edge-case handling fix
2023-01-22 00:03:16 +03:00
AUTOMATIC
78f59a4e01
enable compact view for train tab
...
prevent previews from ruining hypernetwork training
2023-01-22 00:02:51 +03:00
invincibledude
6c0566f937
Type mismatch fix
2023-01-21 23:25:36 +03:00
invincibledude
3bd898b6ce
First test of different sampler for hi-res fix
2023-01-21 23:14:59 +03:00
AUTOMATIC
3deea34135
extract extra network data from prompt earlier
2023-01-21 19:36:08 +03:00
AUTOMATIC
92fb1096db
make it so that extra networks are not removed from infotext
2023-01-21 16:41:25 +03:00
AUTOMATIC
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
AUTOMATIC1111
a8322ad75b
Merge pull request #6854 from EllangoK/master
...
Saves Extra Generation Parameters to params.txt
2023-01-18 23:25:56 +03:00
AUTOMATIC
b186d44dcd
use DDIM in hires fix is the sampler is PLMS
2023-01-18 23:20:23 +03:00
EllangoK
5e15a0b422
Changed params.txt save to after manual init call
2023-01-17 11:42:44 -05:00
AUTOMATIC
e0e8005009
make StableDiffusionProcessing class not hold a reference to shared.sd_model object
2023-01-16 23:09:08 +03:00
AUTOMATIC
9991967f40
Add a check and explanation for tensor with all NaNs.
2023-01-16 22:59:46 +03:00
AUTOMATIC
f9ac3352cb
change hypernets to use sha256 hashes
2023-01-14 10:25:37 +03:00
space-nuko
88416ab5ff
Fix extension parameters not being saved to last used parameters
2023-01-12 13:46:59 -08:00
AUTOMATIC
d4fd2418ef
add an option to use old hiresfix width/height behavior
...
add a visual effect to inactive hires fix elements
2023-01-09 14:57:47 +03:00
noodleanon
50e2536279
Merge branch 'AUTOMATIC1111:master' into img2img-api-scripts
2023-01-07 14:18:09 +00:00
AUTOMATIC
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
2023-01-07 09:56:37 +03:00
noodleanon
b5253f0dab
allow img2img api to run scripts
2023-01-05 21:21:48 +00:00
AUTOMATIC
847f869c67
experimental optimization
2023-01-05 21:00:52 +03:00
AUTOMATIC
2e30997450
move sd_model assignment to the place where we change the sd_model
2023-01-05 10:21:17 +03:00
Philpax
83ca8dd0c9
Merge branch 'AUTOMATIC1111:master' into fix-sd-arch-switch-in-override-settings
2023-01-05 05:00:58 +01:00
AUTOMATIC
99b67cff0b
make hires fix not do anything if the user chooses the second pass resolution to be the same as first pass resolution
2023-01-05 01:25:52 +03:00
AUTOMATIC
bc43293c64
fix incorrect display/calculation for number of steps for hires fix in progress bars
2023-01-04 23:56:43 +03:00
AUTOMATIC
8149078094
added the option to specify target resolution with possibility of truncating for hires fix; also sampling steps
2023-01-04 22:04:40 +03:00
AUTOMATIC
097a90b88b
add XY plot parameters to grid image and do not add them to individual images
2023-01-04 19:19:11 +03:00
AUTOMATIC
525cea9245
use shared function from processing for creating dummy mask when training inpainting model
2023-01-04 17:58:07 +03:00
AUTOMATIC
4d66bf2c0d
add infotext to "-before-highres-fix" images
2023-01-04 17:24:46 +03:00
AUTOMATIC1111
6281c1bdb4
Merge pull request #6299 from stysmmaker/feat/latent-upscale-modes
...
Add more latent upscale modes
2023-01-04 13:47:36 +03:00
MMaker
15fd0b8bc4
Update processing.py
2023-01-04 05:12:54 -05:00
MMaker
e5b7ee910e
fix: Save full res of intermediate step
2023-01-04 04:22:01 -05:00
AUTOMATIC
e9fb9bb0c2
fix hires fix not working in API when user does not specify upscaler
2023-01-03 17:40:20 +03:00
AUTOMATIC
ef27a18b6b
Hires fix rework
2023-01-02 19:42:10 +03:00
AUTOMATIC
f4535f6e4f
make it so that memory/embeddings info is displayed in a separate UI element from generation parameters, and is preserved when you change the displayed infotext by clicking on gallery images
2022-12-31 23:40:55 +03:00
AUTOMATIC
4af3ca5393
make it so that blank ENSD does not break image generation
2022-12-26 10:11:28 +03:00
Philpax
fa931733f6
fix(api): assign sd_model after settings change
2022-12-25 20:17:49 +11:00
AUTOMATIC1111
064f7b8fd2
Merge pull request #5718 from space-nuko/feature/save-hypernetwork-hash
...
Save hypernetwork hash and fix hypernetwork parameter restoring
2022-12-24 11:14:19 +03:00
AUTOMATIC
c0a8401b5a
rename the option for img2img latent upscale
2022-12-24 11:12:17 +03:00
AUTOMATIC1111
b2dbd4d698
Merge pull request #5521 from AndrewRyanChama/ryan/img2imglatentscale
...
Add latent upscale option to img2img
2022-12-24 11:10:35 +03:00
AUTOMATIC1111
7578b50ba6
Merge pull request #5873 from philpax/override-settings-restore-afterwards
...
feat(api): add override_settings_restore_afterwards
2022-12-24 10:15:04 +03:00
AUTOMATIC1111
fac92610d2
Merge pull request #5753 from calvinballing/master
...
Fix various typos
2022-12-24 09:58:28 +03:00
AUTOMATIC
9441c28c94
add an option for img2img background color
2022-12-24 09:46:35 +03:00
Philpax
22f1527fa7
feat(api): add override_settings_restore_afterwards
2022-12-20 20:36:49 +11:00
Jim Hays
c0355caefe
Fix various typos
2022-12-14 21:01:32 -05:00
space-nuko
7077428209
Save hypernetwork hash in infotext
2022-12-13 13:05:40 -08:00
ThereforeGames
2e8b5418e3
Improve color correction with luminosity blend
2022-12-11 18:03:36 -05:00
AUTOMATIC1111
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
AUTOMATIC
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
AUTOMATIC
bab91b1279
add Noise multiplier option to infotext
2022-12-10 09:51:26 +03:00
AUTOMATIC1111
8ee1acc1e4
Merge pull request #5373 from mezotaken/master
...
add noise strength parameter similar to NAI
2022-12-10 09:36:24 +03:00
Jay Smith
1ed4f0e228
Depth2img model support
2022-12-08 20:50:08 -06:00
Andrew Ryan
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
Vladimir Repin
cf3e844d1d
add noise strength parameter similar to NAI
2022-12-03 18:05:47 +03:00
AUTOMATIC1111
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
Adi Eyal
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
Billy Cao
9a8678f61e
Support changing checkpoint and vae through override_settings
2022-11-29 11:11:29 +08:00
klimaleksus
67efee33a6
Make VAE step sequential to prevent VRAM spikes
2022-11-28 16:29:43 +05:00
AUTOMATIC
40ca34b837
fix for broken sampler selection in img2img and xy plot #4860 #4909
2022-11-27 13:17:39 +03:00
AUTOMATIC1111
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
AUTOMATIC
413c077969
prevent StableDiffusionProcessingImg2Img changing image_mask field as an alternative solution to #4765
2022-11-19 13:48:59 +03:00
AUTOMATIC
617c5b486f
make it possible for StableDiffusionProcessing to accept multiple different negative prompts in a batch
2022-11-19 13:23:25 +03:00
AUTOMATIC1111
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
AUTOMATIC
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
AUTOMATIC1111
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
AUTOMATIC
cdc8020d13
change StableDiffusionProcessing to internally use sampler name instead of sampler index
2022-11-19 12:01:51 +03:00
Llewellyn Pritchard
9bbe1e3c2e
Fix unbounded prompt growth scripts that loop
2022-11-16 19:19:00 +02:00
KEV
40ae95d532
Fix retrieving value for 'x/y plot' script.
2022-11-14 18:05:59 +10:00
KEV
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
Billy Cao
c13e234444
Merge branch 'master' into enable-override-hypernet
2022-11-06 16:33:08 +08:00
Billy Cao
55ca040958
Resolve conflict
2022-11-06 16:31:44 +08:00
AUTOMATIC
eeb0733013
change process_one virtual function for script to process_batch, add extra args and docs
2022-11-04 11:21:40 +03:00
AUTOMATIC1111
c250d2a08f
Merge pull request #4182 from macrosoft/process_one
...
Process one
2022-11-04 11:07:05 +03:00
AUTOMATIC
f674c488d9
bugfix: save image for hires fix BEFORE upscaling latent space
2022-11-04 10:45:34 +03:00
AUTOMATIC
f2b69709ea
move option access checking to options class out of various places scattered through code
2022-11-04 09:42:25 +03:00
random-thoughtss
243253ff4a
Merge branch 'AUTOMATIC1111:master' into master
2022-11-03 15:55:54 -07:00
Artem Zagidulin
de64146ad2
add number of itter
2022-11-02 21:30:50 +03:00
Artem Zagidulin
a9e979977a
process_one
2022-11-02 19:05:01 +03:00
AUTOMATIC
eb5e82c7dd
do not unnecessarily run VAE one more time when saving intermediate image with hires fix
2022-11-02 12:45:03 +03:00
timntorres
9c67408004
Allow saving "before-highres-fix. ( #4150 )
...
* Save image/s before doing highres fix.
2022-11-02 12:18:21 +03:00
Jairo Correa
c9148b2312
Release processing resources after it finishes
2022-11-01 21:56:47 -03:00
Billy Cao
bc60768606
Enable override_settings to take effect for hypernetworks
2022-11-01 23:26:55 +08:00
Jairo Correa
af758e97fa
Unload sd_model before loading the other
2022-11-01 04:01:49 -03:00
random_thoughtss
71571e3f05
Replaced master branch fix with updated fix.
2022-10-30 00:35:40 -07:00
random-thoughtss
15468c9939
Merge branch 'AUTOMATIC1111:master' into master
2022-10-30 00:30:18 -07:00
AUTOMATIC
61836bd544
shorten Hypernetwork strength in infotext and omit it when it's the default value.
2022-10-30 08:48:53 +03:00
AUTOMATIC1111
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
AUTOMATIC
05a657dd35
fix broken hires fix
2022-10-30 07:41:56 +03:00
timntorres
e709afb0f7
Merge commit 'e7254746bbfbff45099db44a8d4d25dd6181877d' into 3825-save-hypernet-strength-to-info
2022-10-29 14:55:30 -07:00
random_thoughtss
39f55c3c35
Re-add explicit device move
2022-10-29 14:13:02 -07:00
AUTOMATIC
9bb6b6509a
add postprocess call for scripts
2022-10-29 22:20:02 +03:00
random_thoughtss
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
random_thoughtss
44ab954fab
Fix latent upscale highres fix #3888
2022-10-29 10:02:56 -07:00
timntorres
2c4d203884
Revert "Explicitly state when Hypernet is none."
2022-10-29 00:36:51 -07:00
timntorres
e98f72be33
Merge branch 'AUTOMATIC1111:master' into 3825-save-hypernet-strength-to-info
2022-10-29 00:31:23 -07:00
timntorres
c0677b3316
Explicitly state when Hypernet is none.
2022-10-27 23:31:45 -07:00
timntorres
9e465c8aa5
Add strength to textinfo.
2022-10-27 23:03:34 -07:00
random_thoughtss
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
random-thoughtss
f3f2ffd448
Merge branch 'AUTOMATIC1111:master' into master
2022-10-27 11:19:12 -07:00
AUTOMATIC
1e428238db
add override_settings to API as an alternative to #3629
2022-10-26 11:47:17 +03:00
random_thoughtss
8b4f32779f
Switch to a continous blend for cond. image.
2022-10-25 13:15:08 -07:00
random_thoughtss
605d27687f
Added conditioning image masking to xy_grid.
...
Use `True` and `False` to select values.
2022-10-25 12:20:54 -07:00
random_thoughtss
f9549d1cbb
Added option to use unmasked conditioning image.
2022-10-25 11:14:12 -07:00
AUTOMATIC
6cbb04f7a5
fix #3517 breaking txt2img
2022-10-24 09:15:26 +03:00
Vladimir Repin
f2cc3f32d5
fix whitespaces
2022-10-24 08:58:56 +03:00
Vladimir Repin
9741969325
Save properly processed image before color correction
2022-10-24 08:58:56 +03:00
Stephen
9e1a8b7734
non-implemented mask with any type
2022-10-23 09:26:56 +03:00
Stephen
a7c213d0f5
[API][Feature] - Add img2img API endpoint
2022-10-23 09:26:56 +03:00
AUTOMATIC
ca5a9e79dc
fix for img2img color correction in a batch #3218
2022-10-22 22:06:54 +03:00
AUTOMATIC
324c7c732d
record First pass size as 0x0 for #3328
2022-10-22 20:09:51 +03:00
AUTOMATIC
2b91251637
removed aesthetic gradients as built-in
...
added support for extensions
2022-10-22 12:23:58 +03:00
timntorres
fccad18a59
Refer to Hypernet's name, sensibly, by its name variable.
2022-10-21 16:52:24 +03:00
AUTOMATIC
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
AUTOMATIC
bf30673f51
Fix Hypernet infotext string split bug for PR #3283
2022-10-21 10:19:25 +03:00
AUTOMATIC
4587218190
updated readme and some small stylistic changes to code
2022-10-21 09:00:39 +03:00
random_thoughtss
92a17a7a4a
Made dummy latents smaller. Minor code cleanups
2022-10-20 09:45:03 -07:00
random_thoughtss
aa7ff2a197
Fixed non-square highres fix generation
2022-10-19 21:46:13 -07:00
random_thoughtss
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
random_thoughtss
8e7097d06a
Added support for RunwayML inpainting model
2022-10-19 13:47:45 -07:00
timntorres
5e012e4dfa
Infotext saves more specific hypernet name.
2022-10-19 20:20:25 +03:00
