603509ec90
as per wfjsw's suggestion, revert changes for sd_hijack_checkpoint.py
2024-06-08 10:54:41 +03:00
ad229fae43
Merge pull request #15803 from huchenlei/checkpoint_false
...
[Performance 1/6] use_checkpoint = False
2024-06-08 10:52:40 +03:00
510f025a01
replace wsl-open with wslpath and explorer.exe
2024-06-08 16:52:12 +09:00
c3c90deec0
Merge pull request #15681 from AUTOMATIC1111/fix_p_invalid_sampler_and_scheduler
...
more old sampler scheduler compatibility
2024-06-08 10:42:42 +03:00
ebfc9f6d09
Merge branch 'dev' into patch-4
2024-06-08 10:35:09 +03:00
33b73c473c
Merge pull request #15820 from huchenlei/force_half
...
[Performance 6/6] Add --precision half option to avoid casting during inference
2024-06-08 10:26:23 +03:00
ba54c747e2
Merge pull request #15656 from AUTOMATIC1111/api-old-sampler-names
...
Allow old sampler names in API
2024-06-08 10:18:20 +03:00
15245d9d5e
Merge pull request #15600 from AUTOMATIC1111/fix-corrupt-model-loop
...
Fix corrupt model initial load loop
2024-06-08 10:12:45 +03:00
5429e4cff5
add proper infotext support for #15607
...
fix settings override not working for NGMI, s_churn, etc...
2024-06-08 09:56:09 +03:00
b150b3a3a4
Merge pull request #15607 from drhead/patch-1
...
add code for skipping CFG on early steps
2024-06-08 09:20:08 +03:00
0edc04d126
Merge branch 'dev' into patch-2
2024-06-08 09:10:51 +03:00
00f37ad73f
Merge pull request #15893 from alcacode/dev
...
Fix bug where file extension had an extra '.' under some circumstances
2024-06-08 09:06:03 +03:00
0769aa318a
integrated edits as recommended in the PR #15804
2024-06-08 09:05:35 +03:00
de7f5cdc62
Merge pull request #15804 from huchenlei/rearrange_fix
...
[Performance 2/6] Replace einops.rearrange with torch native ops
2024-06-08 08:55:51 +03:00
46bcfbe37c
Merge pull request #15751 from LoganBooker/LoganBooker-Add-AlignYourSteps-Scheduler
...
Add Align Your Steps to available schedulers
2024-06-08 08:43:02 +03:00
53f62674ae
Typo on edit
...
Edited in fix in Github editor and mistyped from local copy
2024-06-06 16:30:01 -07:00
25bbf31f57
Fix for grids without comprehensive infotexts
...
When generating grids, some scripts such as img2img loopback and ultimate SD upscale do not pass infotexts for each image since they are the same prompt.
If you attempt to save those images using the saved button in the UI it will fail because it will look for the selected image info text. This fixes those errors by replicating the infotext for as many images are passed into the image list if the infotext parameter is none.
2024-06-06 16:22:49 -07:00
6dd53ce63d
Fix bug where file extension had an extra '.' under some circumstances
...
Fix bug where under some circumstances an extra "." was inserted between the file base name and the file extension.
The bug is triggered when the extension argument is one of "jpg", "jpeg", or "webp", and the image exceeds the format's dimension limit. Then the extension variable is set to ".png", resulting in the fullfn variable to evaluate to a string ending with "..png".
2024-05-26 15:36:55 +02:00
feeb6802aa
fix case where first step skilled if skip early cond is 0
2024-05-18 01:22:31 -04:00
1d74482817
Default device for sigma tensor to CPU
...
* Consistent with implementations in k-diffusion.
* Makes this compatible with https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15823
2024-05-18 09:09:57 +10:00
b57a70f373
Proper fix of SD15 dtype
2024-05-17 13:34:04 -04:00
dca9007ac7
Fix SD15 dtype
2024-05-17 13:23:12 -04:00
cc9ca67664
Add transformer forward patch
2024-05-17 13:14:26 -04:00
53d67088ee
Patch timestep embedding to create tensor on-device
2024-05-17 12:12:57 -04:00
01491d303c
Keep sigmas on CPU
2024-05-17 10:36:08 -04:00
47f1d42a7e
Fix for SD15 models
2024-05-16 20:06:04 -04:00
2a8a60c2c5
Add --precision half cmd option
2024-05-16 19:50:06 -04:00
58eec83a54
Fully prevent use_checkpoint
2024-05-16 16:39:02 -04:00
221ac0b9ab
img2img batch upload method
2024-05-16 23:08:24 +04:00
f015b94176
use torch_utils.float64
2024-05-16 23:19:06 +09:00
9c8075ba8e
torch_utils.float64
...
return torch.float64 if device is not mps or xpu, else return torch.float32
2024-05-16 23:16:50 +09:00
3e20b36e8f
Fix attr access
2024-05-15 17:27:01 -04:00
6a48476502
Fix flag check for SD15
2024-05-15 16:54:26 -04:00
9eb2f78631
Precompute is_sdxl_inpaint flag
2024-05-15 16:32:29 -04:00
0e98529365
Replace einops.rearrange with torch native
2024-05-15 15:46:53 -04:00
022d835565
use_checkpoint = False
2024-05-15 15:20:40 -04:00
5ab7d08a0a
fix extention update when not on main branch
2024-05-15 17:27:05 +09:00
d6b4444069
Use shared.sd_model.is_sdxl to determine base AYS sigmas
2024-05-10 18:05:45 +10:00
73d1caf8f2
Add Align Your Steps to available schedulers
...
* Include both SDXL and SD 1.5 variants (https://research.nvidia.com/labs/toronto-ai/AlignYourSteps/howto.html )
2024-05-10 12:38:10 +10:00
5fbac49791
Added --models-dir option
...
The --model-dir option overrides the location of the models directory for stable diffusion, so that models can be shared across multiple installations. When --data-dir is specified alone, both the extensions and models folders are present in this folder. --models-dir can be used independently, but when used with --data-dir, then the models folder is specified by --models-dir, and extensions are found in the --data-dir.
2024-05-08 16:48:10 -04:00
f7e349cea4
Add AVIF MIME type support to mimetype definitions
...
AVIF images will open, rather than download, as the default behaviour.
2024-05-08 21:23:18 +10:00
e736c3b36b
Add files via upload
...
Fixed an error (AttributeError: 'str' object has no attribute 'decode') coming from line 792 in images.py when trying to upscale certain images.
2024-05-08 05:22:12 -04:00
f12886aefa
use script_path for webui root in launch_utils
2024-05-04 23:42:37 +09:00
5d5224b322
fix_p_invalid_sampler_and_scheduler
2024-05-02 02:25:16 +09:00
9d39380705
fix extra batch mode P Transparency
...
red, green, blue = transparency TypeError: cannot unpack non-iterable int object
2024-04-30 19:17:53 +09:00
c8336c45b9
Use existing function for old sampler names
2024-04-30 01:53:41 -06:00
579f1ef278
Allow old sampler names in API
2024-04-28 22:36:43 -06:00
3d3fc81f48
Add correct mimetype for .mjs files
2024-04-28 16:14:12 -04:00
3a215deff2
vectorize kl-optimal sigma calculation
...
Co-authored-by: mamei16 <marcel.1710@live.de>
2024-04-28 00:15:58 -04:00
9d964d3fc3
no-referrer
2024-04-27 19:21:34 +09:00
60c0799958
Linter - except must not be bare.
2024-04-26 08:21:12 -04:00
44afb48447
Linter fix - extraneous whitespace
2024-04-26 08:17:37 -04:00
c5ae225418
Better handling of embeddings with two rare, but not unusual, files in them
...
I have encountered pickled embeddings with a short byteorder file at the top-level, as well as a .data/serialization_id file.
Both load fine after allowing these files in the dataset.
I do not think it is likely adding them to the safe unpickle regular expression would be a security risk, but that's for the maintainers to decide.
2024-04-26 07:55:39 -04:00
c5b7559856
Better error handling when unable to extract contents of embedding/TI file
2024-04-26 06:57:32 -04:00
8dc920228e
Better error handling when unable to read metadata from safetensors file
2024-04-26 06:52:21 -04:00
d5f6fdb3c4
compact-checkbox-group
2024-04-26 18:47:04 +09:00
e85e327ae0
more extension tag filtering options
2024-04-25 13:26:26 +04:00
1091e3a37e
update jpeg_quality description
2024-04-24 02:54:26 +09:00
8fa3fa76c3
fix exif_bytes referenced before assignment
2024-04-24 02:41:31 +09:00
50bb6e1179
AVIF has quality setting too
2024-04-23 18:45:42 +03:00
029adbe531
implement option to skip uncond on all steps below ngms
2024-04-23 03:15:56 -04:00
33cbbf9f8b
add s_min_uncond_all option
2024-04-23 03:15:00 -04:00
6e9b69a338
change skip_early_cond code to use float
2024-04-23 03:08:28 -04:00
83182d2799
change skip early cond option name and to float
2024-04-23 03:07:25 -04:00
83266205d0
Add KL Optimal scheduler
2024-04-23 00:09:43 -04:00
8016d78a4b
add option for early cfg skip
2024-04-22 23:42:24 -04:00
a1aa0af8a4
add code for skipping CFG on early steps
2024-04-22 23:38:44 -04:00
c69773d7e8
ensure integrity for initial sd model download
2024-04-23 03:09:45 +09:00
246c269af8
add option to check file hash after download
...
if the sha256 hash does not match it will be automatically deleted
2024-04-23 03:09:45 +09:00
2b717bb195
fix initial corrupt model loop
...
if for some reason the initial loading model at loading phase of webui is corrupted
after entering this state the user will not be able to load even a good model is selected, due the the unload_model_weights > send_model_to_cpu > m.lowvram attribute check will fail becaules m is None
webui will be stuck in the loop unable to recover without manual intervention
2024-04-23 02:35:25 +09:00
821adc3041
fix get_crop_region_v2
...
Co-Authored-By: Dowon <ks2515@naver.com>
2024-04-22 23:10:19 +09:00
61f6479ea9
restore 1.8.0-style naming of scripts
2024-04-22 12:19:30 +03:00
e4aa0c362e
Merge pull request #15587 from AUTOMATIC1111/fix-mistake-in-#15583
...
fix mistake in #15583
2024-04-22 11:50:34 +03:00
a183ea4ba7
undo adding scripts to sys.modules
2024-04-22 11:49:55 +03:00
6c7c176dc9
fix mistake in #15583
2024-04-22 00:10:49 +09:00
db263df5d5
get_crop_region_v2
2024-04-21 19:34:11 +09:00
c0eaeb15af
Merge pull request #15532 from huchenlei/fix_module
...
Fix cls.__module__ value in extension script
2024-04-21 07:42:57 +03:00
9bcfb92a00
rename logging from textual inversion to not confuse it with global logging module
2024-04-21 07:41:28 +03:00
d74fc56fa5
Merge pull request #15547 from AUTOMATIC1111/numpy-DeprecationWarning-product---prod
...
numpy DeprecationWarning product -> prod
2024-04-21 07:23:38 +03:00
a44ed231c2
Merge pull request #15555 from light-and-ray/fix_x1_upscalers
...
fix x1 upscalers
2024-04-21 07:22:58 +03:00
daae17851a
Merge pull request #15560 from AUTOMATIC1111/api-downscale
...
Remove API upscaling factor limits
2024-04-21 07:22:30 +03:00
6f4f6bff6b
add more info to the error message for #15567
2024-04-21 07:18:58 +03:00
367b823466
Merge pull request #15567 from AUTOMATIC1111/no-image-data-blocks-debug
...
Hide 'No Image data blocks found.' message
2024-04-21 07:09:27 +03:00
c8ac42aad1
Merge pull request #15533 from travisg/callback-fix
...
fix: remove_callbacks_for_function should also remove from the ordered map
2024-04-21 07:07:58 +03:00
449bc7bcf3
Merge pull request #15534 from storyicon/fix-masking
...
Fix images do not match / Coordinate 'right' is less than 'left'
2024-04-21 07:06:45 +03:00
3810413c00
Merge pull request #15581 from AUTOMATIC1111/FilenameGenerator-sampler-scheduler
...
FilenameGenerator Sampler Scheduler
2024-04-21 07:00:28 +03:00
f8f5d6cea2
Merge pull request #15577 from AUTOMATIC1111/api-get-schedulers
...
Add schedulers API endpoint
2024-04-21 06:59:56 +03:00
49fee7c8db
Add avif support
2024-04-20 23:26:04 +03:00
b5b1487f6a
FilenameGenerator Sampler Scheduler
2024-04-21 04:52:03 +09:00
5cb567c138
Add schedulers API endpoint
2024-04-19 20:32:09 -06:00
d212fb59fe
Hide 'No Image data blocks found.' message
2024-04-18 20:56:51 -06:00
71314e47b1
feat:compatible with inconsistent/empty mask
...
Signed-off-by: storyicon <storyicon@foxmail.com>
2024-04-18 11:59:25 +00:00
909c3dfe83
Remove API upscaling factor limits
2024-04-17 21:20:03 -06:00
9d4fdc45d3
fix x1 upscalers
2024-04-18 01:53:23 +04:00
63fd38a04f
numpy DeprecationWarning product -> prod
2024-04-17 15:54:45 +09:00
0980fdfe8c
fix: images do not match
...
Signed-off-by: storyicon <storyicon@foxmail.com>
2024-04-16 07:35:33 +00:00
bba306d414
fix: remove callbacks properly in remove_callbacks_for_function()
...
Like remove_current_script_callback just before, also remove from the
ordered_callbacks_map to keep the callback map and ordered callback map
in sync.
2024-04-15 21:10:11 -07:00
a95326bec4
nit
2024-04-15 22:34:01 -04:00
0f82948e4f
Fix cls.__module__
2024-04-15 22:14:19 -04:00
a196319edf
Merge pull request #15492 from w-e-w/update-restricted_opts
...
update restricted_opts
2024-04-11 19:34:10 +03:00
592e40ebe9
update restricted_opts
2024-04-11 23:10:25 +09:00
4068429ac7
fix: Coordinate 'right' is less than 'left'
...
Signed-off-by: storyicon <storyicon@foxmail.com>
2024-04-10 10:53:25 +00:00
88f70ce63c
Merge pull request #15470 from AUTOMATIC1111/read-infotext-Script-not-found
...
error handling paste_field callables
2024-04-09 16:01:13 +03:00
ef83f6831f
catch exception for all paste_fields callable
2024-04-09 21:32:58 +09:00
600f339c4c
Warning when Script is not found
2024-04-09 21:32:41 +09:00
7f691612ca
Merge pull request #15460 from AUTOMATIC1111/create_infotext-index-and-callable
...
create_infotext allow index and callable, re-work Hires prompt infotext
2024-04-09 12:05:15 +03:00
a976f4dff9
Merge pull request #15460 from AUTOMATIC1111/create_infotext-index-and-callable
...
create_infotext allow index and callable, re-work Hires prompt infotext
2024-04-09 12:05:02 +03:00
696d6813e0
Merge pull request #15465 from jordenyt/fix-extras-api-upscale-enabled
...
Fix extra-single-image API not doing upscale failed
2024-04-09 11:00:49 +03:00
2580235c72
Fix extra-single-image API not doing upscale failed
2024-04-09 11:13:47 +08:00
3786f3742f
fix limited file write (thanks, Sylwia)
2024-04-08 16:15:55 +03:00
d9708c92b4
fix limited file write (thanks, Sylwia)
2024-04-08 16:15:25 +03:00
e3aabe6959
add documentation for create_infotext
2024-04-08 20:14:02 +09:00
1e1176b6eb
non-serializable as None
2024-04-08 18:18:33 +09:00
219e64489c
re-work extra_generation_params for Hires prompt
2024-04-08 18:18:13 +09:00
47ed9b2d39
allow list or callables in generation_params
2024-04-08 01:39:31 +09:00
6efdfe3234
if use use_main_prompt index = 0
2024-04-07 22:58:12 +09:00
2ad17a6100
re-add update_file_entry
...
MassFileLister.update_file_entry was accidentally removed in https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/15205/files#diff-c39b942d8f8620d46d314db8301189b8d6195fc97aedbeb124a33694b738d69cL151-R173
2024-04-06 15:56:57 +09:00
23c06a51cc
use 'scripts.' prefix for names of dynamically loaded modules
2024-04-06 09:05:04 +03:00
badb70da48
Merge pull request #15423 from storyicon/master
...
feat: ensure the indexability of dynamically imported packages
2024-04-06 09:00:35 +03:00
447198f21b
Merge pull request #15442 from AUTOMATIC1111/open_folder-as-util
...
open_folder as util
2024-04-06 08:54:20 +03:00
acb20338b1
put HF_ENDPOINT into shared for #15443
2024-04-06 08:53:21 +03:00
73f7812045
Merge pull request #15443 from Satariall/add-hf_endpoint-variable
...
Use HF_ENDPOINT variable for HuggingFace domain with default
2024-04-06 08:48:55 +03:00
989b89b12a
Use HF_ENDPOINT variable for HuggingFace domain with default
...
Modified the list_models function to dynamically construct the model URL
by using an environment variable for the HuggingFace domain. This allows
for greater flexibility in specifying the domain and ensures that the
modification is also compatible with the Hub client library. By
supporting different environments or requirements without hardcoding the
domain name, this change facilitates the use of custom HuggingFace
domains not only within our code but also when interacting with the Hub
client library.
2024-04-05 13:02:49 +03:00
20123d427b
open_folder docstring
2024-04-05 16:19:20 +09:00
a05d89b1e5
Merge branch 'dev' into open_folder-as-util
2024-04-05 15:14:38 +08:00
92e6aa3653
open_folder as util
2024-04-05 16:08:45 +09:00
b372fb6165
fix API upscale
2024-04-01 23:33:45 +03:00
a669b8a6bc
fix: remove script callbacks in ordered_callbacks_map
2024-04-01 12:51:09 -07:00
e73a7e4006
feat: ensure the indexability of dynamically imported packages
...
Signed-off-by: storyicon <storyicon@foxmail.com>
2024-04-01 09:13:07 +00:00
ea83180761
fix CodeFormer weight
2024-03-31 14:41:06 +02:00
f1a6c5fe17
add an option to hide postprocessing options in Extras tab
2024-03-31 08:30:00 +03:00
dcd4f880a8
rework code/UI for #15293
2024-03-31 08:17:22 +03:00
7f3ce06de9
Merge pull request #15293 from light-and-ray/extras_upscaler_limit_target_resolution
...
Extras upscaler: option limit target resolution
2024-03-31 08:02:35 +03:00
8bebfde701
Merge pull request #15350 from baseco/memory-bug-fix
...
minor bug fix of sd model memory management
2024-03-30 07:37:10 +03:00
98096195dd
Merge pull request #15382 from huaizong/fix/whz/model-loaded-remove-v3
...
fix: when find already_loaded model, remove loaded by array index
2024-03-30 07:36:33 +03:00
642bca4c3d
Merge pull request #15380 from light-and-ray/interrupt_upscale
...
interrupt upscale
2024-03-30 07:34:34 +03:00
4e2bb7250f
fix_ui_config_for_hires_sampler_and_scheduler
2024-03-27 15:35:06 +04:00
c321680b3d
interrupt upscale
2024-03-26 14:53:38 +04:00
f4633cb9c0
fix: when find already_loaded model, remove loaded by array index
2024-03-26 18:29:51 +08:00
f62217b65d
minor bug fix of sd model memory management
2024-03-25 10:38:15 -07:00
dfbdb5a135
put request: gr.Request at start of img2img function similar to txt2img
2024-03-25 18:00:58 +03:00
b0b90dc0d7
Merge pull request #15319 from catboxanon/feat/ssmd_cover_images
...
Support cover images embedded in safetensors metadata
2024-03-24 13:43:37 +03:00
9aa9e980a9
support scheduler selection in hires fix
2024-03-24 11:00:16 +03:00
c4402500c7
Support `ssmd_cover_images`
2024-03-24 02:33:10 -04:00
bf2f7b3af4
Merge pull request #15333 from AUTOMATIC1111/scheduler_selection
...
Scheduler selection in main UI
2024-03-24 05:21:56 +03:00
f3ca6a92ad
Fix for #15333
...
- Fix "X/Y/Z plot" not working with "Schedule type"
- Fix "Schedule type" not being saved to "params.txt"
2024-03-23 00:50:37 +05:00
57727e554d
make #15334 work without making copies of images
2024-03-21 07:22:27 +03:00
b80b1cf92c
Merge pull request #15334 from Gourieff/extras--allow-png-rgba--dev
...
Allow PNG-RGBA for Extras Tab
2024-03-21 07:21:15 +03:00
5c5594ff16
linter
2024-03-21 07:09:40 +03:00
65075896f2
Merge pull request #15310 from Dalton-Murray/update-pytorch-lightning-utilities
...
Update pytorch lightning utilities
2024-03-21 07:08:43 +03:00
AUTOMATIC1111