61836bd544
shorten Hypernetwork strength in infotext and omit it when it's the default value.
3 years ago
470f184176
Merge pull request #3831 from timntorres/3825-save-hypernet-strength-to-info
...
Save Hypernetwork strength to infotext.
3 years ago
05a657dd35
fix broken hires fix
3 years ago
e709afb0f7
Merge commit 'e7254746bbfbff45099db44a8d4d25dd6181877d' into 3825-save-hypernet-strength-to-info
3 years ago
39f55c3c35
Re-add explicit device move
3 years ago
9bb6b6509a
add postprocess call for scripts
3 years ago
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.
3 years ago
44ab954fab
Fix latent upscale highres fix #3888
3 years ago
2c4d203884
Revert "Explicitly state when Hypernet is none."
3 years ago
e98f72be33
Merge branch 'AUTOMATIC1111:master' into 3825-save-hypernet-strength-to-info
3 years ago
c0677b3316
Explicitly state when Hypernet is none.
3 years ago
9e465c8aa5
Add strength to textinfo.
3 years ago
26a3fd2fe9
Highres fix works with unmasked latent.
...
Also refactor the mask creation to make it more accesible.
3 years ago
f3f2ffd448
Merge branch 'AUTOMATIC1111:master' into master
3 years ago
1e428238db
add override_settings to API as an alternative to #3629
3 years ago
8b4f32779f
Switch to a continous blend for cond. image.
3 years ago
605d27687f
Added conditioning image masking to xy_grid.
...
Use `True` and `False` to select values.
3 years ago
f9549d1cbb
Added option to use unmasked conditioning image.
3 years ago
6cbb04f7a5
fix #3517 breaking txt2img
3 years ago
f2cc3f32d5
fix whitespaces
3 years ago
9741969325
Save properly processed image before color correction
3 years ago
9e1a8b7734
non-implemented mask with any type
3 years ago
a7c213d0f5
[API][Feature] - Add img2img API endpoint
3 years ago
ca5a9e79dc
fix for img2img color correction in a batch #3218
3 years ago
324c7c732d
record First pass size as 0x0 for #3328
3 years ago
2b91251637
removed aesthetic gradients as built-in
...
added support for extensions
3 years ago
fccad18a59
Refer to Hypernet's name, sensibly, by its name variable.
3 years ago
df57064093
do not load aesthetic clip model until it's needed
...
add refresh button for aesthetic embeddings
add aesthetic params to images' infotext
3 years ago
bf30673f51
Fix Hypernet infotext string split bug for PR #3283
3 years ago
4587218190
updated readme and some small stylistic changes to code
3 years ago
92a17a7a4a
Made dummy latents smaller. Minor code cleanups
3 years ago
aa7ff2a197
Fixed non-square highres fix generation
3 years ago
c418467c03
Don't compute latent mask if were not using it. Also added support for fixed highres_fix generation.
3 years ago
8e7097d06a
Added support for RunwayML inpainting model
3 years ago
5e012e4dfa
Infotext saves more specific hypernet name.
3 years ago
5daf9cbb98
Merge remote-tracking branch 'origin/api'
3 years ago
cbf15edbf9
remove dependence on TQDM for sampler progress/interrupt functionality
3 years ago
f80e914ac4
example API working with gradio
3 years ago
60251c9456
initial prototype by borrowing contracts
3 years ago
c9836279f5
Only make output dir when creating output
3 years ago
0c5fa9a681
do not reload embeddings from disk when doing textual inversion
3 years ago
97f0727489
add First pass size always regardless of whether it was auto chosen or specified
3 years ago
f7ca63937a
bring back scale latent option in settings
3 years ago
a13af34b90
Set to -1 when seed input is none
3 years ago
368f4cc4c7
set firstpass w/h to 0 by default and rever to old behavior when any are 0
3 years ago
e644b5a80b
remove scale latent and no-crop options from hires fix
...
support copy-pasting new parameters for hires fix
3 years ago
b382de2d77
Fixed Scale ratio problem
3 years ago
40d1c6e423
Option between stretch and crop for Highres. fix
3 years ago
b2261b53ae
Added first_pass_width and height as adjustable inputs to "High Res Fix"
3 years ago
e72adc999b
Restore last generation params
3 years ago
39919c40dd
add eta noise seed delta option
3 years ago
8f1efdc130
--no-half-vae pt2
3 years ago
7349088d32
--no-half-vae
3 years ago
8d340cfb88
do not add clip skip to parameters if it's 1 or 0
3 years ago
ec2bd9be75
Fix issues with CLIP ignore option name change
3 years ago
e6e8cabe0c
change up #2056 to make it work how i want it to plus make xy plot write correct values to images
3 years ago
594cbfd8fb
Sanitize infotext output (for now)
3 years ago
006791c13d
Fix grabbing the model name for infotext
3 years ago
d6d10a37bf
Added extended model details to infotext
3 years ago
bd833409ac
additional changes for saving pnginfo for #1803
3 years ago
ef93acdc73
remove line break
3 years ago
03e570886f
Fix incorrect sampler name in output
3 years ago
050a6a798c
support loading .yaml config with same name as model
...
support EMA weights in processing (????)
3 years ago
432782163a
chore: Fix typos
3 years ago
3b2141c5fb
add 'Ignore last layers of CLIP model' option as a parameter to the infotext
3 years ago
5f85a74b00
fix bug where when using prompt composition, hijack_comments generated before the final AND will be dropped
3 years ago
4999eb2ef9
do not let user choose his own prompt token count limit
3 years ago
00117a07ef
check specifically for skipped
3 years ago
786d9f63aa
Add button to skip the current iteration
3 years ago
706d5944a0
let user choose his own prompt token count limit
3 years ago
1cc36d170a
Added job_timestamp to Processed
...
So `[job_timestamp]` pattern can use in saving image UI.
3 years ago
070b7d60cf
Added styles to Processed
...
So `[styles]` pattern can use in saving image UI.
3 years ago
dbc8a4d351
add generation parameters to images shown in web ui
3 years ago
b66aa334a9
Merge branch 'master' into fix-vram
3 years ago
5993df24a1
integrate the new samplers PR
3 years ago
5f24b7bcf4
option to let users select which samplers they want to hide
3 years ago
c26732fbee
added support for AND from https://energy-based-model.github.io/Compositional-Visual-Generation-with-Composable-Diffusion-Models/
3 years ago
82380d9ac1
Removing parts no longer needed to fix vram
3 years ago
1f50971fb8
Merge branch 'master' into fix-vram
3 years ago
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
3 years ago
e1b128d8e4
do not touch p.seed/p.subseed during processing #1181
3 years ago
52cef36f6b
emergency fix for img2img
3 years ago
6165246124
support interrupting after the previous change
3 years ago
6c6ae28bf5
send all three of GFPGAN's and codeformer's models to CPU memory instead of just one for #1283
3 years ago
ad0cc85d1f
Merge branch 'master' into stable
3 years ago
5f561ee95d
Merge remote-tracking branch 'origin/master'
3 years ago
820f1dc96b
initial support for training textual inversion
3 years ago
9de1e56e2d
add sampler_noise_scheduler_override property
3 years ago
ad1fbbae93
Merge branch 'master' into fix-vram
3 years ago
9a54077d4d
repair broken highres fix #1109
3 years ago
c938679de7
Fix memory leak and reduce memory usage
3 years ago
1deac2b645
do nor add log messages to saved iamge parameters
3 years ago
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)
3 years ago
aea5b2510e
save parameters for images when using the Save button.
3 years ago
5391c0bf3e
Update processing.py
3 years ago
4ea36a37d6
add sampler properties to StableDiffusionProcessing and Processed
3 years ago
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.
3 years ago
31ac0baba0
Reformat some changes from the previous commit.
3 years ago
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
3 years ago
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.
3 years ago
1a0353675d
Option to use advanced upscalers with normal img2img
3 years ago
d26d89377b
Remove unnecessary duplication
3 years ago
25eb1e3d90
Add option to save before color correction. Add suffix param when saving files, used for special saves without color correction and face restoration.
3 years ago
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
3 years ago
75dd274dd6
prevent seed extras from having effect when extras checkbox is not checked
3 years ago
19a75d38d7
added --use-textbox-seed option to make long seeds possible from web ui
3 years ago
06cd206107
Enable neural network upscalers for highres. fix
3 years ago
b9674e2900
add extra generation params
3 years ago
6d7ca54a1a
added highres fix feature
3 years ago
7539f04e28
made 'reuse seed' button give you the seed/subseed of the currently selected picture rather than the first
3 years ago
21086e60a9
Merge remote-tracking branch 'origin/master'
3 years ago
6a28aac866
prevent black screen when seed and variation seed are the same.
3 years ago
4c17ce4949
handle NoneType when subseed is not initialized. Set it to -1 in that case
3 years ago
c76a616bc9
fix many paths in code breaking because Processing constructor changed
3 years ago
a96076f49c
Add buttons for random and reuse seed.
...
Random button sets seed to -1, reuse copies the seed from the last
generated image.
3 years ago
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
3 years ago
f39b2ca088
fixed typos in processing.py
3 years ago
7bc5739fe2
set loopback color corrections on each iteration
3 years ago
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.
3 years ago
247f58a5e7
add support for switching model checkpoints at runtime
3 years ago
b8cf2ea8ea
add a bit of a comment about what's being done with tensor noise
3 years ago
83bce1a604
Merge branch 'batch-seed-attempt'
3 years ago
87e8b9a2ab
prevent replacing torch_randn globally (instead replacing k_diffusion.sampling.torch) and add a setting to disable this all
3 years ago
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
3 years ago
f2693bec08
prompt editing
3 years ago
b28cf84c36
prevent repeating messages about too many tokens
3 years ago
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
3 years ago
6bea45d495
prevent making grid if there is no need for it #428
3 years ago
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
3 years ago
9d40212485
first attempt to produce crrect seeds in batch
3 years ago
7a5852a4ee
change np.float to np.float32
...
* numpy deprecation warning fix. Alternately, you could also specify float
3 years ago
c84e333622
color correction option for all img2img modes #363
3 years ago
b5a8b99d3f
put safety checker into a separate file because it's already crowded in processing
3 years ago
fc18e2d483
Adds NSFW content filter option
3 years ago
19a817d97d
X/Y plot with denoising adds incorrect image data to individual outputs #331
3 years ago
3de44fc580
Include the model name (or the SHA256 of the file) in the metadata #271
3 years ago
c7e0e28ccd
changes for #294
3 years ago
11e03b9abd
Merge pull request #294 from EliasOenal/master
...
Fixes for mps/Metal: use of seeds, img2img, CodeFormer
3 years ago
a655e90fbe
add negative prompt to log when clicking save #249
3 years ago
40f4d3ed98
[FEATURE] Save both images, (Skip_Save optional). #265
3 years ago
b7f95869b4
Refactored Metal/mps fixes.
3 years ago
a1305060ce
Variations are not working properly #305
3 years ago
a4416f3585
[BUG] Not Working As Intended - create a directory with name derived from the prompt #306
3 years ago
81d91cea29
Merge remote-tracking branch 'origin/master'
3 years ago
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.
3 years ago
8fb9c57ed6
add half() supporrt for CLIP interrogation
3 years ago
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.
3 years ago
13008bab90
Fixed prompt_style type hints: int -> str
3 years ago
b3311a50dc
fix repeating subseeds for every batch #221
3 years ago
fbdec2ef20
Fix prompt matrix script
3 years ago
AUTOMATIC
timntorres
random_thoughtss
timntorres
random-thoughtss
Vladimir Repin
Stephen
arcticfaded
CookieHCl
githublsx
Buckzor
Trung Ngo
Fampai
William Moorehouse
frostydad
Aidan Holland
MrCheeze
Milly
Jairo Correa
Rae Fu
DepFA
C43H66N12O12S2
Daniel
RnDMonkey
Jacob Tyndall
Robin Fernandes
berkybear
Johan Aires Rastén
Steve Eberhardt
Brian Drupieski
Tony Beeman
JustAnOkapi
JJ
GRMrGecko
Elias Oenal
Michoko
JohannesGaessler
Lukas Meller