d3113f5c3f
feat: use consistent file name in gradio ( #1932 )
...
* feat: use consistent file name in gradio
returns and uses filepaths instead of numpy image by saving to temp dir
uses double the temp dir file storage on disk as it saves to temp dir and gradio temp dir when displaying the image, but reuses logged output image
* feat: delete temp images after yielding to gradio
* feat: use args temp path if given
* chore: code cleanup, remove redundant if statement
2024-02-25 22:56:38 +01:00
c898e6a4dc
feat: add array support on main prompt ( #1503 )
...
* prompt array support
* update change log
* update change log
* docs: remove 2.1.847 change log
* refactor: rename freeze_seed to disable_seed_increment, move to developer debug mode
* feat: add translation for new labels
* fix: use task_rng based on task_seed, not initial seed
---------
Co-authored-by: Manuel Schmid <manuel.schmid@odt.net>
2024-02-25 22:22:49 +01:00
18f9f7dc31
feat: make lora number editable in config ( #2215 )
...
* Initial commit
* Update README.md
* sync with original main Fooocus repo
* update with my gitignore setup
* add max lora config feature
* Revert "add max lora config feature"
This reverts commit cfe7463fe2
2024-02-25 21:12:26 +01:00
468d704b29
feat: add button to enable LoRAs ( #2210 )
...
* Initial commit
* Update README.md
* sync with original main Fooocus repo
* update with my gitignore setup
* add max lora config feature
* Revert "add max lora config feature"
This reverts commit cfe7463fe2
2024-02-25 19:59:28 +01:00
7cfb5e742d
feat: add advanced parameter for disable_intermediate_results (progress_gallery) ( #1013 )
...
* add advanced parameter for disable_intermediate_results
prevents gradio frontend process from clogging image output and updates in high throughput scenarios such as LCM with image number >= 4
* update disable_intermediate_results correctly
based on default and selected performance
* chore: add missing translations
2024-02-25 11:31:00 +01:00
5b7ddf8b22
feat: advanced params refactoring + prevent users from skipping/stopping other users tasks in queue ( #981 )
...
* only make stop_button and skip_button interactive when rendering process starts
fix inconsistency in behaviour of stop_button and skip_button as it was possible to skip or stop other users processes while still being in queue
* use AsyncTask for last_stop handling instead of shared
* Revert "only make stop_button and skip_button interactive when rendering process starts"
This reverts commit d3f9156854
2024-02-24 19:01:06 +01:00
1d606ecb7e
feat: optimize image censoring
...
Does not save 2x to file (log and yield), but only once (log).
2024-02-24 18:09:45 +01:00
4905f3f2fa
fix: use correct format for upscale metadata
2024-02-24 17:50:40 +01:00
741a693083
feat: add ByteDance lightning preset, code cleanup
2024-02-22 23:02:58 +01:00
5e3816a8b3
fix: add nsfw filter support again
...
accidentally deleted when merging
2024-02-19 23:12:33 +01:00
26601a99d1
Merge branch 'feature/add-metadata-to-files'
2024-02-18 16:27:29 +01:00
267d5eee7d
Merge commit '1c999be8c8134fe01a75723ea933858435856950'
...
# Conflicts:
# .github/ISSUE_TEMPLATE/bug_report.md
# launch.py
# modules/async_worker.py
# modules/config.py
# modules/private_logger.py
# modules/util.py
# webui.py
2024-02-12 21:13:36 +01:00
f4a8bf24cf
fix: correctly calculate refiner switch when overwrite_switch is > 0 ( #2165 )
...
When using custom steps, the calculation of switching timing is wrong. Now it is modified to calculate "steps x timing" after custom steps are used.
By @xhoxye
2024-02-11 15:13:20 +01:00
eb3f4d745c
feat: add suffix ordinals ( #845 )
...
* add suffix ordinals with lambda
* delay importing of modules.config (#2195 )
* refactor: use easier to read version to find matching ordinal suffix
---------
Co-authored-by: rsl8 <138326583+rsl8@users.noreply.github.com>
Co-authored-by: Manuel Schmid <manuel.schmid@odt.net>
Co-authored-by: Manuel Schmid <9307310+mashb1t@users.noreply.github.com>
2024-02-10 21:49:23 +01:00
ceefba9b69
Merge branch 'feature/add-metadata-to-files'
...
# Conflicts:
# language/en.json
# modules/async_worker.py
# modules/config.py
# modules/flags.py
# modules/meta_parser.py
# modules/private_logger.py
# modules/util.py
# webui.py
2024-02-04 21:09:24 +01:00
8af73e622f
chore: remove remaining todos after analysis
...
refiner is added when set
restoring multiline prompts has been resolved by using separate parameters "raw_prompt" and "raw_negative_prompt"
2024-02-04 00:44:26 +01:00
ed4a958da8
fix: add workaround for multiline prompts
2024-02-02 22:04:28 +01:00
f745d40687
refactor: merge metadata.py into meta_parser.py
2024-02-02 01:55:32 +01:00
e55870124b
refactor: add step before parsing to set data in parser
...
- add constructor for MetadataSchema class
- remove showable and copyable from log output
- add functional hash cache (model hashing takes about 5 seconds, only required once per model, using hash lazy loading)
2024-02-02 01:25:47 +01:00
9bdb65ec5d
feat: add metadata handling for all non-img2img parameters
2024-01-31 01:18:09 +01:00
89c8e3a812
feat: make sha256 with length 10 default
2024-01-29 21:54:39 +01:00
e541097451
wip: code cleanup, update todos
2024-01-29 21:54:22 +01:00
33d644f4a5
feat: add prefix "Fooocus" to version
2024-01-29 16:29:40 +01:00
7fefe3a3c2
feat: add created_by again
2024-01-29 16:28:47 +01:00
c80011b1d1
fix: use correct LoRA mapping, add fallback for backwards compatibility
2024-01-29 15:45:55 +01:00
20e53028a4
refactor: use central flag for ControlNet image count
2024-01-29 14:27:51 +01:00
c3ab9f1f30
refactor: use central flag for LoRA count
2024-01-29 14:26:56 +01:00
cbc63ebba3
feat: add enums for Performance, Steps and StepsUOV
...
also move MetadataSchema enum to prevent circular dependency
2024-01-28 20:01:33 +01:00
e19596c2df
feat: map basic information for scheme A1111
2024-01-28 18:04:40 +01:00
f3010313fc
wip: add metadata mapping, reading and writing
...
applying data after reading currently not functional for A1111
2024-01-28 05:35:44 +01:00
051faf78b8
fix: use correct default value in metadata check for created_by
2024-01-25 23:49:25 +01:00
20b79788a0
feat: add resolved prompts to metadata
2024-01-25 23:48:47 +01:00
d7c1f4a6aa
Merge branch 'hotfix/prevent-skipping-and-stopping-by-other-users'
...
# Conflicts:
# modules/advanced_parameters.py
# modules/async_worker.py
# webui.py
2024-01-22 23:15:18 +01:00
148eddf48d
Merge branch 'feature/extract-advanced-parameters' into hotfix/prevent-skipping-and-stopping-by-other-users
...
# Conflicts:
# webui.py
2024-01-22 21:31:24 +01:00
031b1f8b11
chore: cleanup pid code
2024-01-22 21:20:17 +01:00
21f4767c65
fix: resolve circular import, patch_all now in async_worker
2024-01-22 21:14:54 +01:00
177075ff7b
feat: extract remaining attributes, do not use globals in patch
2024-01-22 21:13:44 +01:00
f3222b0f27
feat: extract attribute controlnet_softness
2024-01-22 20:09:24 +01:00
78d2ec8d77
chore: cleanup code
2024-01-22 20:01:43 +01:00
4ce27aeb0f
feat: extract inpaint_ctrls attributes
...
debugging_inpaint_preprocessor, inpaint_disable_initial_latent, inpaint_engine, inpaint_strength, inpaint_respective_field, inpaint_mask_upload_checkbox, invert_mask_checkbox, inpaint_erode_or_dilate
2024-01-22 19:20:04 +01:00
eb1d3938fe
feat: extract freeu_ctrls attributes
...
freeu_enabled, freeu_b1, freeu_b2, freeu_s1, freeu_s2
2024-01-22 19:19:40 +01:00
cfb70c0278
feat: extract attribute refiner_swap_method
2024-01-22 19:10:32 +01:00
2d8ca41ce5
feat: extract attribute canny_high_threshold
2024-01-22 19:08:54 +01:00
ec486443ea
feat: extract attribute canny_low_threshold
2024-01-22 19:06:10 +01:00
9f194a91fa
feat: extract attribute skipping_cn_preprocessor
2024-01-22 18:54:25 +01:00
0bf41591a6
feat: extract attribute debugging_cn_preprocessor
2024-01-22 18:52:41 +01:00
6289e5daea
feat: extract attribute mixing_image_prompt_and_inpaint
2024-01-22 18:51:12 +01:00
cce9871cc5
feat: extract attribute mixing_image_prompt_and_vary_upscale
2024-01-22 18:49:29 +01:00
2ab5593d71
feat: extract attribute overwrite_upscale_strength
2024-01-22 18:46:47 +01:00
22af976c51
feat: extract attribute overwrite_vary_strength
2024-01-22 18:45:01 +01:00
9f4a00e868
feat: extract attribute overwrite_height
2024-01-22 18:42:54 +01:00
2eed5a28f2
feat: extract attribute overwrite_width
2024-01-22 18:41:02 +01:00
2b1f501462
feat: extract attribute overwrite_switch
2024-01-22 18:38:20 +01:00
df35033cc9
feat: extract attribute overwrite_step
2024-01-22 18:34:40 +01:00
217be190bb
feat: extract attribute generate_image_grid
2024-01-22 18:23:10 +01:00
d72573aca4
feat: extract attribute scheduler_name
2024-01-22 18:06:11 +01:00
e54bad87f1
feat: extract attribute sampler_name
2024-01-22 18:00:27 +01:00
fc3da75baf
feat: extract attribute adaptive_cfg
2024-01-22 17:31:18 +01:00
618b01764c
feat: extract attribute adm_scaler_end
2024-01-22 17:11:27 +01:00
64dcdbbef3
feat: extract attribute adm_scaler_negative
2024-01-22 17:03:50 +01:00
3607059224
feat: extract attribute adm_scaler_positive
2024-01-22 17:01:32 +01:00
79a63491fe
feat: extract attribute disable_preview
2024-01-22 16:58:46 +01:00
72d1e48def
Merge branch 'jpg_config_image_extension'
...
# Conflicts:
# modules/async_worker.py
# modules/flags.py
# modules/private_logger.py
# webui.py
2024-01-19 00:14:44 +01:00
7e52a1de8f
refactor: rename image_file_extension to output_format
2024-01-19 00:06:07 +01:00
addd5ef3bd
Merge branch 'feature/add-metadata-to-files'
...
# Conflicts:
# args_manager.py
# modules/async_worker.py
# modules/config.py
# modules/private_logger.py
# modules/util.py
2024-01-16 00:50:46 +01:00
ba5d0b6eaf
refactor: rename metadata_schema to metadata_scheme
2024-01-15 23:59:57 +01:00
80ad0d070e
fix: do not generate hashes when arg --disable-metadata is used
2024-01-15 23:58:34 +01:00
cd65f21d98
fix: use stting isntead of quote wrap for A1111 created_by
2024-01-15 23:14:49 +01:00
7b9deb17ee
feat: add config metadata_created_by
2024-01-15 23:06:20 +01:00
6662381931
fix: code cleanup and resolved prompt fixes
2024-01-15 23:00:59 +01:00
1a52367f3f
feat: use resolved prompts with included expansion and styles for a1111 metadata
2024-01-15 22:17:51 +01:00
f7489cc9ef
feat: add model hash support for a1111
2024-01-15 22:11:46 +01:00
191f8148e4
feat: add support for A1111 metadata schema
...
cf2772fab0/modules/processing.py (L672)
2024-01-15 21:16:52 +01:00
493e484122
feat: add argument disable_metadata
2024-01-15 19:11:40 +01:00
8d56318bed
feat: add config and checkbox for save_metadata_to_images
2024-01-15 18:54:49 +01:00
c5a15c7321
feat: add metadata logging for images
...
inspired by https://github.com/MoonRide303/Fooocus-MRE
2024-01-15 18:31:58 +01:00
f25bf49894
Merge branch 'jpg_config_image_extension'
...
# Conflicts:
# modules/config.py
# modules/flags.py
# webui.py
2024-01-14 23:40:24 +01:00
5b633f6cf8
refactor: rename image_extension to image_file_extension
2024-01-14 23:38:36 +01:00
b18ae4343d
Merge branch 'jpg_config_image_extension'
...
# Conflicts:
# modules/async_worker.py
# modules/config.py
# modules/flags.py
# webui.py
2024-01-14 23:22:03 +01:00
dc6c02540a
Merge branch 'feature/use-consistent-file-name-in-gradio' into jpg_config_image_extension
...
# Conflicts:
# modules/async_worker.py
# modules/private_logger.py
2024-01-14 21:47:05 +01:00
3c855bd331
feat: use consistent file name in gradio
...
returns and uses filepaths instead of numpy image by saving to temp dir
uses double the temp dir file storage on disk as it saves to temp dir and gradio temp dir when displaying the image, but reuses logged output image
2024-01-14 20:21:33 +01:00
694763447d
fix: add missing image_extension parameter to log call
2024-01-14 14:23:36 +01:00
ab3acb7817
moved image extension to webui via async worker. Passing as parameter to log and get_current_html_path functions per feedback
2024-01-12 22:49:07 -08:00
2e16b0faa4
Merge remote-tracking branch 'origin/hotfix/prevent-skipping-and-stopping-by-other-users'
...
# Conflicts:
# modules/async_worker.py
2024-01-05 22:59:09 +01:00
e68c8aa0a7
Merge branch 'main_upstream' into hotfix/prevent-skipping-and-stopping-by-other-users
...
# Conflicts:
# webui.py
2024-01-04 18:07:06 +01:00
ee3d70ab87
fix: replace fcbh with ldm_patched
2024-01-04 18:03:12 +01:00
925ba509f7
Merge branch 'main_upstream'
...
# Conflicts:
# modules/advanced_parameters.py
2024-01-02 18:00:26 +01:00
e5af760db8
mask upload
2024-01-02 08:21:50 -08:00
b5163e057f
Fooocus mask enhance, mask upload and invert.蒙版增强功能，上传蒙版、反转手涂蒙版 ( #1645 )
...
* Update webui.py
Added a mask upload interface.添加蒙版上传界面。
* Add mask upload feature
Add mask upload feature.添加蒙版上传功能。
* Add mask upload feature
Add mask upload feature.添加蒙版上传功能。
* Try to fix the problem when drawing mates with external enrichment.
Swap the judgment criteria and try to fix the problem when drawing mates with external enrichment.
调换判断条件，尝试修复和外部扩充绘制配合时出现的问题
* 修改注释
* 修改注释
* Update readme.md
更新日志
* Add mask upload check box,
Add check box, default does not show mask upload box, check it and then show it.
添加复选框，默认不显示蒙版上传框，勾选后再显示。
* back to normal
还原
* Try adding a mask inversion feature
Try adding a mask inversion feature.
尝试添加蒙版反转功能。
增加一个复选框来决定是否将蒙版反转。
* Try adding a mask inversion feature
Try adding a mask inversion feature.
尝试添加蒙版反转功能。
增加一个复选框来决定是否将蒙版反转。
* Fixed word errors
* Fix the words of the description
2024-01-02 07:17:02 -08:00
0ab7dd0ce0
Merge branch 'main_upstream' into hotfix/prevent-skipping-and-stopping-by-other-users
2023-12-27 18:43:59 +01:00
3ba59df559
add default_overwrite_step handling for meta data and gradio
...
allows turbo preset switching to set default_overwrite_step correctly
2023-12-24 23:31:46 +01:00
fc909a3a28
Merge branch 'main_upstream'
2023-12-23 16:40:20 +01:00
7b5bced6c2
small url fix ( #1551 )
2023-12-22 00:20:09 -08:00
f7bb578a14
2.1.854
...
* Add a button to copy parameters to clipboard in log.
* Allow users to load parameters directly by pasting parameters to prompt.
2023-12-20 19:52:38 -08:00
a5ed897e21
Merge branch 'main_upstream'
2023-12-20 18:11:07 +01:00
7a6b46f363
New Log System
2023-12-17 20:20:02 -08:00
f47c57a2e5
Merge branch 'feature/add-nsfw-filter'
...
# Conflicts:
# modules/advanced_parameters.py
# webui.py
2023-12-16 23:01:55 +01:00
e97008d4fb
add checkbox black_out_nsfw
...
makes both enabling via config and checkbox possible, where config overrides the checkbox value
2023-12-16 22:55:25 +01:00
1f9d9999db
Merge remote-tracking branch 'upstream/main'
2023-12-14 23:01:49 +01:00
5496ec41a8
Merge remote-tracking branch 'upstream/main' into hotfix/prevent-skipping-and-stopping-by-other-users
...
# Conflicts:
# modules/async_worker.py
# webui.py
2023-12-14 22:58:12 +01:00
323af5667a
2.1.840
...
* Fix some potential frozen after model mismatch
* Fix crash when cfg=1 when using anime preset
* Added some guidelines for troubleshoot the "CUDA kernel errors asynchronously" problem
2023-12-14 13:55:49 -08:00
ea764855f8
Merge remote-tracking branch 'upstream/main' into feature/add-nsfw-filter
...
# Conflicts:
# modules/async_worker.py
# modules/config.py
2023-12-14 22:55:45 +01:00
07fba58c99
Merge remote-tracking branch 'upstream/main'
...
# Conflicts:
# modules/async_worker.py
# requirements_versions.txt
# webui.py
2023-12-14 22:49:29 +01:00
5b99e3a1e4
2.1.839
2023-12-13 21:14:50 -08:00
e8d88d3e25
2.1.826
2023-12-12 11:38:05 -08:00
92a54cff22
Merge branch 'feature/add-prompt-translate'
2023-11-26 11:23:38 +01:00
8718e80dc2
move import as it checks for users ip and geolocation
...
Only metadata of users who specifically activated the prompt translate checkbox should be requested.
This also prevented users with adblockers on DNS level from being able to generate images, now fixed.
2023-11-26 11:23:02 +01:00
298a807a1b
Merge branch 'feature/add-prompt-translate'
...
# Conflicts:
# requirements_versions.txt
# webui.py
2023-11-26 00:14:12 +01:00
25c3184ddc
move prompt translation to async_worker
2023-11-25 23:26:29 +01:00
a5f3e4af9b
Merge branch 'hotfix/prevent-skipping-and-stopping-by-other-users'
...
# Conflicts:
# modules/config.py
2023-11-20 22:01:40 +01:00
8acb2d7537
Merge branch 'main_upstream' into hotfix/prevent-skipping-and-stopping-by-other-users
...
# Conflicts:
# webui.py
2023-11-20 22:00:08 +01:00
dececbd060
[2.1.822] New Inpaint System
...
See related documents for more details.
2023-11-19 17:37:22 -08:00
d7f9fe9732
Merge branch 'hotfix/prevent-skipping-and-stopping-by-other-users'
2023-11-19 23:30:29 +01:00
d2cc9a4fc8
reset last_stop when skipping for further processing
2023-11-19 23:30:18 +01:00
9b680c51a8
Merge branch 'hotfix/prevent-skipping-and-stopping-by-other-users'
...
# Conflicts:
# webui.py
2023-11-19 22:57:58 +01:00
ebad9ea976
introduce state for task skipping/stopping
2023-11-18 20:51:54 +01:00
617255d040
use AsyncTask for last_stop handling instead of shared
2023-11-18 17:20:41 +01:00
2e1e82941d
rebase changes of main for easier handling
2023-11-18 12:58:05 +01:00
3dc69a5293
fix progressbar call for nsfw output
2023-11-18 12:17:06 +01:00
6893c8dd48
Merge commit '8f9f020e8f90efb3787f0feb0e544539110e40ce' into feature/add-nsfw-filter
...
# Conflicts:
# modules/async_worker.py
2023-11-18 12:03:09 +01:00
675805960a
2.1.821
...
* New UI for LoRAs.
* Improved preset system: normalized preset keys and file names.
* Improved session system: now multiple users can use one Fooocus at the same time without seeing others' results.
* Improved some computation related to model precision.
* Improved config loading system with user-friendly prints.
2023-11-17 11:25:39 -08:00
52ae346c9d
add nsfw image censoring
...
activatable via config, uses CompVis/stable-diffusion-safety-checker
2023-11-15 22:00:45 +01:00
a662567f6c
fix #936
2023-11-15 02:25:49 -08:00
cec0c2a8df
2.1.808
...
* Aspect ratios now show aspect ratios.
* Added style search.
* Added style sorting/ordering/favorites.
2023-11-14 14:06:12 -08:00
6c812b68db
add preprocessor skip
2023-11-13 14:35:23 -08:00
ac8002d2a4
speed up lcm again
2023-11-12 09:12:09 -08:00
649f45a6df
'Extreme Speed' performance mode
2023-11-12 07:55:44 -08:00
54f4b265e0
lcm scheduler
2023-11-12 06:44:44 -08:00
e6aeefd2b4
only load libs when necessary
2023-11-12 02:16:11 -08:00
e7fe1d443a
only load libs when necessary
2023-11-12 02:10:48 -08:00
2bef62c545
2.1.790
...
2.1.790
2023-11-11 22:13:13 -08:00
4fe08161a5
2.1.782
...
2.1.782
2023-11-11 01:43:01 -08:00
a9bb1079cf
disable refiner when same as base
2023-11-08 23:39:57 -08:00
2165114876
disable image grid
...
disable image grid by default because many users reports performance issues. like #829 and so on.
2023-11-05 19:09:20 -08:00
34bcfa79c0
improve gpt2
...
improve gpt2
2023-10-30 16:40:50 -07:00
759bfadefa
fix async load order + image wall
2023-10-28 23:03:35 -07:00
f07f7693d3
fix refiner
2023-10-26 19:42:50 -07:00
4607316c2f
get each image during generating
...
get each image during generating
2023-10-26 17:17:05 -07:00
9982d34b6c
safer deep copy
2023-10-26 10:29:30 -07:00
823fa924d3
disable expansion when empty since it is not meaningful and influences image prompt
...
disable expansion when empty since it is not meaningful and influences image prompt
2023-10-26 08:59:49 -07:00
175f3e3040
update backend + revise styles
...
update backend + revise styles
2023-10-26 08:24:45 -07:00
214c2ba04c
fix resize
2023-10-25 21:02:55 -07:00
38e70cebcc
Update Backend
...
Update Backend
2023-10-25 09:40:13 -07:00
523aa190db
Refactored handling max random seed
2023-10-24 12:15:43 +02:00
60cb91c406
allow ar config
2023-10-23 19:42:23 -07:00
81650a4305
Increased allowed random seed range
2023-10-23 12:27:12 +02:00
d4a9b116e4
fix log for multiple-line prompts
2023-10-20 05:15:49 -07:00
ff8d649cac
bfs for wildcard
2023-10-20 05:05:29 -07:00
04066124c2
fix many resolution problems
2023-10-20 02:41:04 -07:00
37da4ac13a
Cleaned up Private Log (most users won't need information about raw prompts)
2023-10-20 11:07:23 +02:00
Manuel Schmid
Brian Flannery
MindOfMatter
Manuel Schmid
Manuel Schmid
hisk2323
eddyizm
lllyasviel
xhoxye
Huy Nguyen
MoonRide303