Mirror/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2024-06-07 21:20:49 +00:00
Code Issues Packages Projects Releases Wiki Activity
7,084 Commits 35 Branches 33 Tags 305 MiB
2bb296531d
Commit Graph

4474 Commits

Author SHA1 Message Date
AUTOMATIC1111
04a005f0e9
Merge pull request #14512 from AUTOMATIC1111/remove-excessive-extra-networks-reload 
reduce unnecessary re-indexing extra networks directory
 2024-01-03 19:15:46 +03:00
w-e-w
fccd0b00c2 reduce unnecessary re-indexing extra networks dir 2024-01-03 19:25:06 +09:00
Aarni Koskela
7ad6899bf9 torch_bgr_to_pil_image: round, don't truncate 
This matches what `realesrgan` does.
 2024-01-02 17:14:05 +02:00
Aarni Koskela
2cacbc124c load_spandrel_model: make half prefer_half 
As discussed with the Spandrel folks, it's good to heed Spandrel's
"supports half precision" flag to avoid e.g. black blotches and what-not.
 2024-01-02 10:44:38 +02:00
Aarni Koskela
cf14a6a7aa Refactor upscale_2 helper out of ScuNET/SwinIR; make sure devices are right 2024-01-02 08:57:12 +02:00
AUTOMATIC1111
980970d390 final touches 2024-01-02 07:08:32 +03:00
AUTOMATIC1111
80873b1538 fix #14497 2024-01-02 07:05:05 +03:00
AUTOMATIC1111
1341b22081 add an option to hide upscaling progressbar 2024-01-02 06:47:26 +03:00
Jibaku789
a5b6a5a3ad
Add inpaint options to img2img.py 2024-01-01 14:58:55 -06:00
Jibaku789
c2ea571005
Add inpaint options to paste fields 2024-01-01 14:57:41 -06:00
AUTOMATIC1111
501993ebf2 added a button to run hires fix on selected image in the gallery 2024-01-01 19:31:06 +03:00
AUTOMATIC1111
5d7d1823af rename infotext.py again, this time to infotext_utils.py; I didn't realize infotext would be used for variable names in multiple places, which makes it awkward to import the module; also fix the bug I caused by this rename that breaks tests 2024-01-01 17:25:30 +03:00
AUTOMATIC1111
1ffdedc11d restore lines lost from #13789 merge 2024-01-01 17:03:08 +03:00
AUTOMATIC1111
7ba02e0b7c
Merge branch 'dev' into finer-settings-freezing-control 2024-01-01 17:01:06 +03:00
AUTOMATIC1111
15156cde18
Merge pull request #14291 from AUTOMATIC1111/on-mouse-hover-show-hide-modal-image-viewer-icons 
on mouse hover show / hide modal image viewer icons
 2024-01-01 16:53:33 +03:00
AUTOMATIC1111
0aa7c53c0b fix borked merge, rename fields to better match what they do, change setting default to true for #13653 2024-01-01 16:50:59 +03:00
AUTOMATIC1111
dfd6438221
Merge branch 'dev' into feat/interrupted-end 2024-01-01 16:39:51 +03:00
AUTOMATIC1111
0ce67cb618
Merge pull request #14352 from AUTOMATIC1111/reduce-unnecessary-ui-config-write 
only rewrite ui-config when there is change
 2024-01-01 16:35:07 +03:00
AUTOMATIC1111
cba6fba123
Merge pull request #14353 from Nuullll/ipex-sdpa 
[IPEX] Slice SDPA into smaller chunks
 2024-01-01 16:33:55 +03:00
AUTOMATIC1111
ac0ecf3b4b option to convert VAE to bfloat16 (implementation of #9295) 2024-01-01 16:28:58 +03:00
AUTOMATIC1111
d8126be578 linter 2024-01-01 15:00:39 +03:00
AUTOMATIC1111
45b7bba3d0 add automatic version support for zero terminal SNR noise schedule option from #14145 2024-01-01 14:51:56 +03:00
AUTOMATIC1111
267fd5d76b
Merge pull request #14145 from drhead/zero-terminal-snr 
Implement zero terminal SNR noise schedule option
 2024-01-01 14:45:12 +03:00
AUTOMATIC1111
d613cd17c7 add automatic backwards version compatibility 2024-01-01 14:38:29 +03:00
AUTOMATIC1111
d859cec696 infotext.py: rename usages in the codebase 2024-01-01 13:53:12 +03:00
AUTOMATIC1111
c5496c7646 infotext.py: add support for old modules.generation_parameters_copypaste name 2024-01-01 13:52:37 +03:00
AUTOMATIC1111
003b91f083 rename generation_parameters_copypaste module to infotext 2024-01-01 13:45:18 +03:00
AUTOMATIC1111
5692bf1517 add missing field for DDIM sampler that was breaking img2img 2024-01-01 11:11:14 +03:00
w-e-w
00901bfbe0 handle selectable script_index is None 2024-01-01 15:47:57 +09:00
AUTOMATIC1111
a70dfb64a8 change import statements for #14478 2023-12-31 22:38:30 +03:00
AUTOMATIC1111
be5f1acc8f
Merge pull request #14478 from akx/dtype-inspect 
Add utility to inspect a model's dtype/device
 2023-12-31 22:33:32 +03:00
AUTOMATIC1111
f3af8c8d04
Merge pull request #14475 from Learwin/negative_prompt 
Adding negative prompts to Loras in extra networks
 2023-12-31 22:32:28 +03:00
Learwin
b6f74e936e Revert change from linting for unrelated file 2023-12-31 13:36:36 +01:00
Aarni Koskela
5768afc776 Add utility to inspect a model's parameters (to get dtype/device) 2023-12-31 13:22:43 +02:00
Aarni Koskela
6f86b62a1b Deduplicate tiled inference code from SwinIR/ScuNET 2023-12-31 01:13:30 +02:00
Aarni Koskela
777af661a2 Be more clear about Spandrel model nomenclature 2023-12-31 00:22:58 +02:00
Aarni Koskela
c0ca6348e8 load_spandrel_model: always return a model descriptor 2023-12-31 00:04:47 +02:00
AUTOMATIC1111
3be9074031 fix for the previous fix. 2023-12-31 00:43:41 +03:00
Learwin
a2f23f9d22 Code Style fixes 2023-12-30 22:16:51 +01:00
Learwin
bc5ae74c7d Added negative prompts to extra networks lora 2023-12-30 21:52:27 +01:00
AUTOMATIC1111
8100e901ab fix error with RealESRGAN model failing to upscale fp32 image 2023-12-30 22:41:53 +03:00
AUTOMATIC1111
c2fd7c0344
Merge pull request #14474 from akx/realesrgan-is-esrgan 
Correct RealESRGAN expected architecture type to ESRGAN
 2023-12-30 22:40:11 +03:00
AUTOMATIC1111
7c13ffdbb1
Merge pull request #14472 from akx/drop-move-code 
Remove `cleanup_models` code
 2023-12-30 22:15:30 +03:00
Aarni Koskela
393a5b82ba Correct RealESRGAN expected architecture type to ESRGAN 2023-12-30 21:12:32 +02:00
Aarni Koskela
af050dcaa7 Soften Spandrel model-architecture check to just a warning 2023-12-30 21:05:59 +02:00
Aarni Koskela
5fbb13e0da Remove cleanup_models code 2023-12-30 20:47:12 +02:00
AUTOMATIC1111
16848f950b
Merge pull request #14467 from akx/drop-basicsr 
Drop basicsr dependency
 2023-12-30 21:27:33 +03:00
Aarni Koskela
1465dab715 Make Tensorboard a late import (it was implicitly installed by basicsr) 2023-12-30 19:44:05 +02:00
AUTOMATIC1111
79c9151802
Merge pull request #14421 from lanyeeee/api_thread_safe 
fix API thread safe issues of txt2img and img2img
 2023-12-30 20:21:13 +03:00
lanyeeee
f651405427 remove locks, move init code to __init__ 2023-12-31 01:09:13 +08:00
Aarni Koskela
c9174253fb Drop dependency on basicsr 2023-12-30 17:53:19 +02:00
lanyeeee
91560e98c4 fix format issue 2023-12-30 23:42:10 +08:00
Aarni Koskela
f476649c02 Correct arg type for restore_face 2023-12-30 17:41:29 +02:00
AUTOMATIC1111
cd12c0e15c
Merge pull request #14425 from akx/spandrel 
Use Spandrel for upscaling and face restoration architectures
 2023-12-30 18:06:31 +03:00
AUTOMATIC1111
05230c0260 fix img2img api that i broke when implementing infotext support 2023-12-30 18:02:51 +03:00
Aarni Koskela
4ad0c0c0a8 Verify architecture for loaded Spandrel models 2023-12-30 16:37:03 +02:00
Aarni Koskela
c756133541 Add experimental HAT model 2023-12-30 16:30:49 +02:00
Aarni Koskela
b621a63cf6 Unify CodeFormer and GFPGAN restoration backends, use Spandrel for GFPGAN 2023-12-30 16:30:49 +02:00
Aarni Koskela
b0f5934234 Use Spandrel for upscaling and face restoration architectures (aside from GFPGAN and LDSR) 2023-12-30 16:24:01 +02:00
Aarni Koskela
e472383acb Refactor esrgan_upscale to more generic upscale_with_model 2023-12-30 16:24:01 +02:00
Aarni Koskela
12c6f37f8e Add tile_count property to Grid 2023-12-30 16:24:01 +02:00
Aarni Koskela
7aa27b000a Add types to split_grid 2023-12-30 16:24:01 +02:00
AUTOMATIC1111
31992eff9b make it possible again to extract styles that have whitespace at the end. 2023-12-30 16:51:13 +03:00
kurisu_u
d05f9e8124
Merge branch 'dev' into api_thread_safe 2023-12-30 21:47:59 +08:00
lanyeeee
c069c2c562 add locks to ensure init args are thread-safe 2023-12-30 21:32:22 +08:00
AUTOMATIC1111
4b6eb8072b
Merge pull request #14407 from AUTOMATIC1111/prevent-crash-due-to-Script-__init__-exception 
prevent crash due to Script __init__ exception
 2023-12-30 14:54:31 +03:00
AUTOMATIC1111
908fb4ea71
Merge pull request #14390 from wangqyqq/sdxl-inpaint 
Supporting for SDXL-Inpaint Model
 2023-12-30 14:49:52 +03:00
AUTOMATIC1111
c9c105c7db
Merge pull request #14446 from AUTOMATIC1111/base-output-path-off-data_path 
Base output path off data path
 2023-12-30 14:45:28 +03:00
AUTOMATIC1111
a79890efd6
Merge pull request #14452 from AUTOMATIC1111/save-info-of-init-image 
save info of init image
 2023-12-30 14:41:39 +03:00
AUTOMATIC1111
8f18263759 fix bad values read from infotext for API, add comment 2023-12-30 13:48:25 +03:00
AUTOMATIC1111
11a435b469 img2img support for infotext API 2023-12-30 13:34:46 +03:00
AUTOMATIC1111
0aacd4c72b add support for alwayson scripts for infotext API 2023-12-30 13:33:18 +03:00
AUTOMATIC1111
8b08b78c03 make it so that if an option from infotext conflicts with an argument from API, the latter overrides the former 2023-12-30 12:27:23 +03:00
AUTOMATIC1111
ba92135a2b add override_settings support for infotext API 2023-12-30 12:11:09 +03:00
AUTOMATIC1111
bb07cb6a0d a 2023-12-30 10:42:42 +03:00
w-e-w
dc57ec0296 save info of init image 2023-12-29 01:56:48 +09:00
w-e-w
892e703b59 webpath use truncate_path 2023-12-28 06:52:41 +09:00
w-e-w
af2951ed53 base default image output on data_path 
Co-Authored-By: Alberto Cano <34340962+canoalberto@users.noreply.github.com>
 2023-12-28 06:52:33 +09:00
w-e-w
de04573438 create utility truncate_path 
utli.truncate_path(target_path, base_path)
return the target_path relative to base_path if target_path is a sub path of base_path else return the absolute path
 2023-12-28 06:22:51 +09:00
wangqyqq
bfe418a58d add some codes for robust 2023-12-27 10:20:56 +08:00
lanyeeee
00d4a4d4ac move thread-unsafe code to __init__ 2023-12-26 14:46:29 +08:00
w-e-w
edfae95d90 prevent crash due to Script __init__ exception 2023-12-23 01:21:00 +09:00
wangqyqq
9feb034e34 support for sdxl-inpaint model 2023-12-21 20:15:51 +08:00
Nuullll
f586f4973a Fix device id 2023-12-18 19:44:52 +08:00
Nuullll
e4b4a9c4ac [IPEX] Slice SDPA into smaller chunks 2023-12-18 18:01:09 +08:00
w-e-w
10945aa41a only rewrite ui-config when there is change 
and a typo
 2023-12-18 15:27:41 +09:00
AUTOMATIC1111
de03882d6c make task ids for API work without force_task_id 2023-12-17 08:55:35 +03:00
Kohaku-Blueleaf
a978320334 Let fp8-related settings to invalidate cond_cache 2023-12-16 19:39:43 +08:00
AUTOMATIC1111
86b3aa94e2 rename pending tasks api endpoint to be more in line with others 2023-12-16 11:04:59 +03:00
AUTOMATIC1111
5b7d86d42b
Merge pull request #14314 from gayshub/master 
Add allow specify the task id and get the location of task in the queue of pending task
 2023-12-16 11:01:42 +03:00
AUTOMATIC1111
cd9ce2e31c Use radio for FP8 mode selection 2023-12-16 10:40:20 +03:00
AUTOMATIC1111
8edb9144cc
Merge branch 'dev' into test-fp8 2023-12-16 10:22:16 +03:00
AUTOMATIC1111
7745db6fc0 torch 2.1.2 2023-12-16 10:15:08 +03:00
Kohaku-Blueleaf
ea272152e0 Add FP8 settings into PNG info 2023-12-16 15:08:08 +08:00
AUTOMATIC1111
e9c6325fc6 Merge branch 'dev' into torch210 2023-12-16 10:05:10 +03:00
AUTOMATIC1111
0dfffe53ec Merge pull request #14307 from AUTOMATIC1111/default-Falst-js_live_preview_in_modal_lightbox 
default False js_live_preview_in_modal_lightbox
 2023-12-16 09:25:33 +03:00
gayshub
6d7e57ba6a fix the problem of ruff of github 2023-12-15 18:03:14 +08:00
gayshub
da45e73b4f fix the problem of ruff of github 2023-12-15 17:57:58 +08:00
gayshub
d859de37d9 fix the problem of ruff of github 2023-12-15 17:48:20 +08:00
gayshub
1242ba08e1 add allow specify the task id and get the location of task in the queue of pending task 2023-12-15 16:57:17 +08:00
w-e-w
0c5427960b make modal toolbar and icon opacity adjustable 2023-12-15 17:11:59 +09:00
w-e-w
3c0c277579 default False js_live_preview_in_modal_lightbox 2023-12-15 00:48:37 +09:00
Kohaku-Blueleaf
0fb34b57b8 Merge branch 'dev' into test-fp8 2023-12-14 16:54:45 +08:00
AUTOMATIC1111
eb52c803b8 Merge pull request #14216 from wfjsw/state-dict-ref-comparison 
change state dict comparison to ref compare
 2023-12-14 10:15:22 +03:00
AUTOMATIC1111
f8871dedcf Merge pull request #14230 from AUTOMATIC1111/add-option-Live-preview-in-full-page-image-viewer 
add option: Live preview in full page image viewer
 2023-12-14 10:15:18 +03:00
AUTOMATIC1111
b7e0d4a7e1 Merge pull request #14229 from Nuullll/ipex-embedding 
[IPEX] Fix embedding and ControlNet
 2023-12-14 10:14:59 +03:00
AUTOMATIC1111
5cb1ce470d Merge pull request #14266 from kaalibro/dev 
Re-add setting lost as part of e294e46
 2023-12-14 10:14:54 +03:00
AUTOMATIC1111
888b928f0d Merge pull request #14276 from AUTOMATIC1111/fix-styles 
Fix styles
 2023-12-14 10:14:50 +03:00
AUTOMATIC1111
96c393a7a7
Merge pull request #14269 from kaalibro/skip-interrupt-keyb-shortcuts 
Add keyboard shortcuts for generate/skip/interrupt
 2023-12-14 10:04:17 +03:00
AUTOMATIC1111
09013b357c
Merge pull request #14216 from wfjsw/state-dict-ref-comparison 
change state dict comparison to ref compare
 2023-12-14 10:03:14 +03:00
AUTOMATIC1111
d45f790f58
Merge pull request #14230 from AUTOMATIC1111/add-option-Live-preview-in-full-page-image-viewer 
add option: Live preview in full page image viewer
 2023-12-14 09:59:48 +03:00
AUTOMATIC1111
8c32594d3b
Merge pull request #14208 from CodeHatchling/soft-inpainting 
Soft Inpainting
 2023-12-14 09:56:12 +03:00
AUTOMATIC1111
f3cc5f8382
Merge pull request #14229 from Nuullll/ipex-embedding 
[IPEX] Fix embedding and ControlNet
 2023-12-14 09:52:23 +03:00
AUTOMATIC1111
28bafffdc2
Merge pull request #14266 from kaalibro/dev 
Re-add setting lost as part of e294e46
 2023-12-14 09:48:36 +03:00
kaalibro
1d42babd32
Replace Ctrl+Alt+Enter with Esc 2023-12-10 16:28:56 +06:00
w-e-w
8b74389e76 fix styles.csv filename 2023-12-10 15:48:16 +09:00
w-e-w
23a0e60b9b fix save styles 2023-12-10 15:48:00 +09:00
drhead
5381405eaa
re-derive sqrt alpha bar and sqrt one minus alphabar 
This is the only place these values are ever referenced outside of training code so this change is very justifiable and more consistent.
 2023-12-09 14:09:28 -05:00
kaalibro
9c201550dd
Add keyboard shortcuts for generation 
(Removed Alt+Enter) Ctrl+Enter to start/restart generation
(New) Alt/Option+Enter to skip generation
(New) Ctrl+Alt/Option+Enter to interrupt generation
 2023-12-09 21:04:45 +06:00
kaalibro
39ec4cfea9
Re-add setting lost as part of e294e46 2023-12-09 19:12:59 +06:00
Nuullll
049d5642e5 Fix format 2023-12-09 18:11:26 +08:00
Nuullll
5942979344 Fix ControlNet 2023-12-09 18:09:45 +08:00
CodeHatchling
0ef4a4cb23 Fixed error that occurs when using vanilla samplers (somehow). 2023-12-07 14:54:26 -07:00
CodeHatchling
56604f08a1 Moved image filters used by soft inpainting into soft_inpainting.py from images.py 2023-12-07 14:53:44 -07:00
CodeHatchling
2abc417834 Re-implemented soft inpainting via a script. Also fixed some mistakes with the previous hooks, removed unnecessary formatting changes, removed code that I had forgotten to. 2023-12-07 14:28:02 -07:00
CodeHatchling
ac45789123 Removed soft inpainting, added hooks for softpainting to work instead. 2023-12-06 21:16:27 -07:00
CodeHatchling
4608f6236f Removed changes in some scripts since the arguments for soft painting are no longer passed through the same path as "mask_blur". 2023-12-06 18:11:17 -07:00
CodeHatchling
e90d4334ad A custom blending function can be provided by p, replacing the use of soft_inpainting. 2023-12-06 18:02:07 -07:00
w-e-w
9d2cbf8e97 add option: Live preview in full page image viewer 
make #13459 "show the preview image in the modal view if available" optional
 2023-12-06 23:06:32 +09:00
Nuullll
746783f7a4 [IPEX] Fix embedding 
Cast `torch.bmm` args into same `dtype`.

Fixes the following error when using Text Inversion embedding (#14224):

```
RuntimeError: could not create a primitive descriptor for a matmul
primitive
```
 2023-12-06 20:55:47 +08:00
Kohaku-Blueleaf
294ec5ac37 Merge branch 'dev' into test-fp8 2023-12-06 15:16:49 +08:00
Kohaku-Blueleaf
672dc4efa8 Fix forced reload 2023-12-06 15:16:10 +08:00
Jabasukuriputo Wang
895456c4a2
change state dict comparison to ref compare 2023-12-05 18:00:48 -06:00
AUTOMATIC1111
120a84bd2f Merge pull request #14203 from AUTOMATIC1111/remove-clean_text() 
remove clean_text()
 2023-12-05 07:15:54 +03:00
CodeHatchling
38864816fa Merge remote-tracking branch 'origin2/dev' into soft-inpainting 
# Conflicts:
#	modules/processing.py
 2023-12-04 20:38:13 -07:00
CodeHatchling
49bbf11407 Fixed unused import. 2023-12-04 19:47:40 -07:00
CodeHatchling
6fc12428e3 Fixed issue where batched inpainting (batch size > 1) wouldn't work because of mismatched tensor sizes. The 'already_decoded' decoded case should also be handled correctly (tested indirectly). 2023-12-04 19:42:59 -07:00
CodeHatchling
b32a334e3d Applies a convert('RGBA') operation early to mimic previous behaviour. 2023-12-04 17:57:10 -07:00
CodeHatchling
60c602232f Restored original formatting. 2023-12-04 17:55:14 -07:00
CodeHatchling
57f29bd61d Re-introduce latent blending step from the vanilla inpainting procedure. 2023-12-04 17:41:18 -07:00
CodeHatchling
1455159cf4 Fixed issue with whitespace, removed commented out code that was meant to be used as a reference. 2023-12-04 16:43:57 -07:00
CodeHatchling
976c1053ef Cleaned up code, moved main code contributions into soft_inpainting.py 2023-12-04 16:06:58 -07:00
w-e-w
854f8c318c remove clean_text() 2023-12-05 04:41:09 +09:00
AUTOMATIC1111
81105ee013 repair old handler for postprocessing API in a way that doesn't break interface 2023-12-04 13:11:12 +03:00
AUTOMATIC1111
883d6a2b34 repair old handler for postprocessing API in a way that doesn't break interface 2023-12-04 13:11:00 +03:00
AUTOMATIC1111
24dae9bc4c repair old handler for postprocessing API 2023-12-04 12:36:56 +03:00
AUTOMATIC1111
15322e1b1a repair old handler for postprocessing API 2023-12-04 12:36:41 +03:00
CodeHatchling
259d33c3c8 Enables the original functionality to be toggled on and off. 2023-12-04 01:57:21 -07:00
Kohaku-Blueleaf
f5f89780cc Merge branch 'dev' into test-fp8 2023-12-04 16:47:41 +08:00
CodeHatchling
aaacf48232 Organized the settings and UI of soft inpainting to allow for toggling the feature, and centralizes default values to reduce the amount of copy-pasta. 2023-12-04 01:27:22 -07:00
AUTOMATIC1111
9e1f3feb12 make webui not crash when running with --disable-all-extensions option 2023-12-04 09:15:19 +03:00
AUTOMATIC1111
208760f348
Merge pull request #14192 from illtellyoulater/patch-1 
Update launch_utils.py - fixes repetead package reinstalls
 2023-12-04 08:14:40 +03:00
missionfloyd
06725af40b
Lint 2023-12-03 21:26:12 -07:00
illtellyoulater
639ccf254b
Update launch_utils.py to fix wrong dep. checks and reinstalls 
Fixes failing dependency checks for extensions having a different package name and import name (for example ffmpeg-python / ffmpeg), which currently is causing the unneeded reinstall of packages at runtime.

In fact with current code, the same string is used when installing a package and when checking for its presence, as you can see in the following example:

> launch_utils.run_pip("install ffmpeg-python", "required package")
[ Installing required package: "ffmpeg-python" ... ]
[ Installed ]

> launch_utils.is_installed("ffmpeg-python")
False

... which would actually return true with:

> launch_utils.is_installed("ffmpeg")
True
 2023-12-04 02:35:35 +00:00
CodeHatchling
552f8bc832 "Uncrop" the original denoised image for the composite step, fixing a "ValueError: Images do not match" *shudder* 2023-12-03 14:49:41 -07:00
CodeHatchling
28a2b5b4aa Fixed a math mistake. 2023-12-03 14:20:20 -07:00
AUTOMATIC1111
334298d473
Merge pull request #14186 from akx/torchvision-basicsr-hack 
Add import_hook hack to work around basicsr/torchvision incompatibility
 2023-12-03 19:58:53 +03:00
Aarni Koskela
d92ce145bb Add import_hook hack to work around basicsr incompatibility 
Fixes #13985
 2023-12-03 16:55:38 +02:00
w-e-w
d3fdc4af61 rework mask and mask_composite logic 2023-12-03 18:22:41 +09:00
AUTOMATIC1111
b4776ea3a2
Merge pull request #14177 from catboxanon/fix/mask-composite-save 
Fix `save_samples` being checked early when saving masked composite
 2023-12-03 11:57:14 +03:00
CodeHatchling
3bd3a09160 Merge remote-tracking branch 'origin/dev' into soft-inpainting 
# Conflicts:
#	modules/processing.py
 2023-12-02 21:14:02 -07:00
CodeHatchling
bb04d400c9 Rewrote latent_blend() to use in-place operations and to aggressively "del" references with the intention of minimizing allocations and easing garbage collection. 2023-12-02 21:08:26 -07:00
CodeHatchling
73ab982d1b Blend masks are now produced afterward, based on an estimate of the visual difference between the original and modified latent images. This should remove ghosting and clipping artifacts from masks, while preserving the details of largely unchanged content. 2023-12-02 21:07:02 -07:00
Kohaku-Blueleaf
9a15ae2a92 Merge branch 'dev' into test-fp8 2023-12-03 10:54:54 +08:00
CodeHatchling
609dea36ea Added utility functions related to processing masks. 2023-12-02 18:56:49 -07:00
catboxanon
9528d66c94 Re-add setting lost as part of e294e46 2023-12-02 14:56:26 -05:00
drhead
78acdcf677 fix variable 2023-12-02 14:09:18 -05:00
drhead
dc1adeecdd Create alphas_cumprod_original on full precision path 2023-12-02 14:06:56 -05:00
drhead
4a43334376 Revert 309a606c 2023-12-02 14:05:42 -05:00
catboxanon
83e8c32276 Fix save_samples being checked early when saving masked composite 2023-12-02 13:30:53 -05:00
drhead
81c4ddf6eb
fix linting 2023-12-02 13:11:00 -05:00
drhead
309a606c2f
ensure that original alpha bar always exists 2023-12-02 13:07:45 -05:00
AUTOMATIC1111
ac02216e54 alternate implementation for unet forward replacement that does not depend on hijack being applied 2023-12-02 19:35:47 +03:00
AUTOMATIC1111
af5f0734c9
Merge pull request #14171 from Nuullll/ipex 
Initial IPEX support for Intel Arc GPU
 2023-12-02 19:22:32 +03:00
AUTOMATIC1111
a5f61aa8c5 potential fix for #14172 2023-12-02 18:03:34 +03:00
AUTOMATIC1111
11d23e8ca5 remove Train/Preprocessing tab and put all its functionality into extras batch images mode 2023-12-02 18:01:11 +03:00
Kohaku-Blueleaf
50a21cb09f Ensure the cached weight will not be affected 2023-12-02 22:06:47 +08:00
Nuullll
96871e4f74 Remove webui-ipex-user.bat 2023-12-02 17:11:31 +08:00
AUTOMATIC1111
4a666381bf extras tab batch: actually use original filename 
preprocessing upscale: do not do an extra upscale step if it's not needed
 2023-12-02 12:11:21 +03:00
Kohaku-Blueleaf
110485d5bb Merge branch 'dev' into test-fp8 2023-12-02 17:00:09 +08:00
Nuullll
87cd07b3af Fix fp64 2023-12-02 15:54:25 +08:00
AUTOMATIC1111
0bb6e00ba3
Merge pull request #13957 from h43lb1t0/extra_network_subdirs 
dir buttons start with / so only the correct dir will be shown and no…
 2023-12-02 09:59:29 +03:00
AUTOMATIC1111
87d973e389
Merge pull request #14063 from wfjsw/use-ext-name-for-installed 
use extension name for determining an extension is installed in the index
 2023-12-02 09:58:44 +03:00
AUTOMATIC1111
ef6b8123dc put code that can cause an exception into its own function for #14120 2023-12-02 09:57:39 +03:00
AUTOMATIC1111
5ed7daa3d9
Merge pull request #14120 from AUTOMATIC1111/protect-against-bad-ui-creation-scripts 
catch uncaught exception with ui creation scripts
 2023-12-02 09:54:21 +03:00
AUTOMATIC1111
ef1723ef41
Merge pull request #14125 from cjj1977/dev 
Allow use of mutiple styles csv files
 2023-12-02 09:53:27 +03:00
AUTOMATIC1111
88736b5557
Merge pull request #14131 from read-0nly/patch-1 
Update devices.py - Make 'use-cpu all' actually apply to 'all'
 2023-12-02 09:46:19 +03:00
AUTOMATIC1111
9eadc4f146
Merge pull request #14121 from AUTOMATIC1111/fix-Auto-focal-point-crop-for-opencv-4.8.x 
Fix auto focal point crop for opencv >= 4.8
 2023-12-02 09:46:00 +03:00
AUTOMATIC1111
97c8e7e0c7
Merge pull request #14119 from AUTOMATIC1111/add-Block-component-creation-callback 
add Block component creation callback
 2023-12-02 09:45:03 +03:00
AUTOMATIC1111
e12a26c253
Merge pull request #14046 from hidenorly/AddFP32FallbackSupportOnSdVaeApprox 
Add FP32 fallback support on sd_vae_approx
 2023-12-02 09:44:00 +03:00
AUTOMATIC1111
4125552752
Merge pull request #14170 from MrCheeze/sd-turbo 
Add support for SD 2.1 Turbo
 2023-12-02 09:30:07 +03:00
AUTOMATIC1111
e294e46d46 split UI settings page into many 2023-12-02 09:26:38 +03:00
Nuullll
7499148ad4 Disable ipex autocast due to its bad perf 2023-12-02 14:00:46 +08:00
AUTOMATIC1111
b58d061e41 infotext updates: add option to disregard certain infotext fields, add option to not include VAE in infotext, add explanation to infotext settings page, move some options to infotext settings page 2023-12-02 08:33:28 +03:00
MrCheeze
6080045b2a Add support for SD 2.1 Turbo, by converting the state dict from SGM to LDM on load 2023-12-01 22:58:05 -05:00
MrCheeze
293f44e6c1 Fix bug where is_using_v_parameterization_for_sd2 fails because the sd_hijack is only partially undone 2023-12-01 22:56:08 -05:00
Nuullll
8b40f475a3 Initial IPEX support 2023-11-30 20:22:46 +08:00
drhead
668ae34e21
remove debug print 2023-11-29 22:48:31 -05:00
catboxanon
de79597ab9 Only apply ztSNR related code if alphas_cumprod exists 2023-11-29 18:33:32 -05:00
catboxanon
ffa7f8201d Lint 2023-11-29 18:10:43 -05:00
catboxanon
ec6ee5c13b Fix infotext for ztSNR 2023-11-29 18:10:27 -05:00
drhead
6d0a8dcd89
Implement zero terminal SNR schedule option 2023-11-29 17:42:07 -05:00
drhead
588a52891d
Add options for zero terminal SNR 2023-11-29 17:40:23 -05:00
drhead
b25c126ccd
Protect alphas_cumprod from downcasting 2023-11-29 17:38:53 -05:00
CodeHatchling
c7a1ff8720 Tweaked default values. 2023-11-28 23:31:10 -07:00
CodeHatchling
284fd8f415 Tweaked UI sliders and labels. 2023-11-28 23:03:50 -07:00
CodeHatchling
c5c7fa06aa Added slider for detail preservation strength, removed largely needless offset parameter, changed labels in UI and for saving to/pasting data from PNG files. 2023-11-28 22:35:07 -07:00
CodeHatchling
debf836fcc Added UI elements to control blending parameters. 2023-11-28 16:15:36 -07:00
CodeHatchling
a6e5846453 Nerfs the aggressive post-processing step of overlaying the original image. 2023-11-28 16:13:42 -07:00
CodeHatchling
e715e46b6a Implements "scheduling" for blending of the original latents and a latent blending formula that preserves details in blend transition areas. 2023-11-28 16:10:22 -07:00
CodeHatchling
bbba133f05 Removed conflicting step that replaces the softly inpainted latents with a naive blend with the original latents. 2023-11-28 15:09:43 -07:00
CodeHatchling
dec791d35d Removed code which forces the inpainting mask to be 0 or 1. Now fractional values (e.g. 0.5) are accepted. 2023-11-28 15:05:01 -07:00
hidenorly
81c00728b8 Fix the Ruff error about unused import 2023-11-29 04:59:35 +09:00
hidenorly
a0096c5897 Add FP32 fallback support on torch.nn.functional.interpolate 
This tries to execute interpolate with FP32 if it failed.

Background is that
on some environment such as Mx chip MacOS devices, we get error as follows:

```
"torch/nn/functional.py", line 3931, in interpolate
        return torch._C._nn.upsample_nearest2d(input, output_size, scale_factors)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    RuntimeError: "upsample_nearest2d_channels_last" not implemented for 'Half'
```

In this case, ```--no-half``` doesn't help to solve. Therefore this commits add the FP32 fallback execution to solve it.

Note that the ```upsample_nearest2d``` is called from ```torch.nn.functional.interpolate```.
And the fallback for torch.nn.functional.interpolate is necessary at
```modules/sd_vae_approx.py``` 's ```VAEApprox.forward```
```repositories/stable-diffusion-stability-ai/ldm/modules/diffusionmodules/openaimodel.py``` 's ```Upsample.forward```
 2023-11-29 04:45:04 +09:00
hidenorly
39eae9f009 Revert "Add FP32 fallback support on sd_vae_approx" 
This reverts commit 58c19545c8.
Since the modification is expected to move to mac_specific.py
(https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/14046#issuecomment-1826731532)
 2023-11-29 04:07:48 +09:00
w-e-w
d608926f81 reformat file with uniform indentation 2023-11-28 12:12:27 +09:00
w-e-w
03ee297aa2 fix Auto focal point crop for opencv >= 4.8.x 
autocrop.download_and_cache_models
in opencv >= 4.8 the face detection model was updated
download the base on opencv version
returns the model path or raise exception
 2023-11-28 12:09:51 +09:00
obsol
3cd6e1d0a0
Update devices.py 
fixes issue where "--use-cpu" all properly makes SD run on CPU but leaves ControlNet (and other extensions, I presume) pointed at GPU, causing a crash in ControlNet caused by a mismatch between devices between SD and CN

https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/14097
 2023-11-27 19:21:43 -05:00
Charlie Joynt
26a0c29587 Allow use of mutiple styles csv files 
* https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/14122
Fix edge case where style text has multiple {prompt} placeholders
* https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/14005
 2023-11-27 12:08:51 +00:00
w-e-w
8a6e4bda21 catch uncaught exception with ui creation scripts 
prevent total webui crash
 2023-11-27 14:18:17 +09:00
w-e-w
b30cc87b78 add Block component creation callback 2023-11-27 13:15:17 +09:00
Jabasukuriputo Wang
1f6844eb7e
also consider extension url 2023-11-26 10:04:39 -06:00
AUTOMATIC1111
f0f100e67b add categories to settings 2023-11-26 17:56:22 +03:00
w-e-w
a15dd151ff json.dump(ensure_ascii=False) 
improve json readability
 2023-11-26 21:56:21 +09:00
AUTOMATIC1111
2a40d3c603 compact prompt layout: preserve scroll when switching between lora tabs 2023-11-26 14:58:56 +03:00
Kohaku-Blueleaf
3d341ebc7d Merge branch 'dev' into test-fp8 2023-11-26 17:32:52 +08:00
AUTOMATIC1111
29f04149b6 update torch to 2.1.0 2023-11-26 12:07:33 +03:00
AUTOMATIC1111
6955c210b7
Merge pull request #14059 from akx/upruff 
Update Ruff to 0.1.6
 2023-11-26 11:54:36 +03:00
AUTOMATIC1111
c5a0c59a83 do not save HTML explanations from options page to config 2023-11-26 11:36:17 +03:00
AUTOMATIC1111
f7f015e84b
Merge pull request #14084 from wfjsw/move-from-sysinfo-to-errors 
Move exception_records related methods to errors.py
 2023-11-26 11:29:27 +03:00
AUTOMATIC1111
f85b74763d Merge branch 'hypertile-in-sample' into dev 2023-11-26 11:18:49 +03:00
AUTOMATIC1111
fd8674a4bc
Merge pull request #13948 from aria1th/hypertile-in-sample 
support HyperTile optimization
 2023-11-26 11:18:25 +03:00
AUTOMATIC1111
d2e0c1ca13 rework hypertile into a built-in extension 2023-11-26 11:17:38 +03:00
AUTOMATIC1111
3a9bf4ac10 move file 2023-11-26 08:29:12 +03:00
Kohaku-Blueleaf
40ac134c55 Fix pre-fp8 2023-11-25 12:35:09 +08:00
Jabasukuriputo Wang
5cedc8f9b2
remove traceback in sysinfo 2023-11-24 11:30:30 -06:00
Jabasukuriputo Wang
86b99b1e98
Move exception_records related methods to errors.py 2023-11-24 11:28:54 -06:00
wfjsw
ac2a981c4f use extension name for determining an extension is installed in the index 2023-11-22 22:40:24 -06:00
Aarni Koskela
066afda2f6 Simplify restart_sampler (suggested by ruff) 2023-11-22 18:05:12 +02:00
Kohaku-Blueleaf
f5d719d1f1 Add forced reload for fp16 cache 2023-11-22 01:45:56 +08:00
Kohaku-Blueleaf
370a77f8e7 Option for using fp16 weight when apply lora 2023-11-21 19:59:34 +08:00
AUTOMATIC1111
8aa51f682c fix [Bug]: (Dev Branch) Placing "Dimensions" first in "ui_reorder_list" prevents start #14047 2023-11-21 08:32:07 +03:00
hidenorly
58c19545c8 Add FP32 fallback support on sd_vae_approx 
This tries to execute interpolate with FP32 if it failed.

Background is that
on some environment such as Mx chip MacOS devices, we get error as follows:

```
"torch/nn/functional.py", line 3931, in interpolate
        return torch._C._nn.upsample_nearest2d(input, output_size, scale_factors)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
    RuntimeError: "upsample_nearest2d_channels_last" not implemented for 'Half'
```

In this case, ```--no-half``` doesn't help to solve. Therefore this commits add the FP32 fallback execution to solve it.

Note that the submodule may require additional modifications. The following is the example modification on the other submodule.

```repositories/stable-diffusion-stability-ai/ldm/modules/diffusionmodules/openaimodel.py

class Upsample(nn.Module):
..snip..
    def forward(self, x):
        assert x.shape[1] == self.channels
        if self.dims == 3:
            x = F.interpolate(
                x, (x.shape[2], x.shape[3] * 2, x.shape[4] * 2), mode="nearest"
            )
        else:
            try:
                x = F.interpolate(x, scale_factor=2, mode="nearest")
            except:
                x = F.interpolate(x.to(th.float32), scale_factor=2, mode="nearest").to(x.dtype)
        if self.use_conv:
            x = self.conv(x)
        return x
..snip..
```

You can see the FP32 fallback execution as same as sd_vae_approx.py.
 2023-11-21 01:13:53 +09:00
Tom Haelbich
314ae1535e added option for default behavior of dir buttons 2023-11-20 16:19:54 +01:00
AUTOMATIC1111
5f36f6ab21
Merge pull request #14009 from AUTOMATIC1111/Option-to-show-batch-img2img-results-in-UI 
Option to show batch img2img results in UI
 2023-11-20 17:44:58 +03:00
AUTOMATIC1111
1463cea949 Merge branch 'dag' into dev 2023-11-20 14:50:01 +03:00
AUTOMATIC1111
73a0b4bba6
Merge pull request #13944 from wfjsw/dag 
implementing script metadata and DAG sorting mechanism
 2023-11-20 14:49:46 +03:00
AUTOMATIC1111
9b471436b2 rework extensions metadata: use custom sorter that doesn't mess the order as much and ignores cyclic errors, use classes with named fields instead of dictionaries, eliminate some duplicated code 2023-11-20 14:47:09 +03:00
w-e-w
6d337bf23d save sysinfo as .json 
GitHub now allows uploading of .json files in issues
 2023-11-20 01:38:31 +09:00
w-e-w
dea5e43c83 Option to show batch img2img results in UI 
shared.opts.img2img_batch_show_results_limit
limit the number of images return to the UI for batch img2img
default limit 32
0 no images are shown
-1 unlimited, all images are shown
 2023-11-19 17:37:32 +09:00