Commit Graph

418 Commits

Author SHA1 Message Date
Manuel Schmid 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
Brian Flannery 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
MindOfMatter 3be76ef8a3
feat: make lora min max weight editable in config (#2216)
* Initial commit

* Update README.md

* sync with original main Fooocus repo

* update with my gitignore setup

* add min max weight configs feature

* add max lora config feature

* Revert "add max lora config feature"

This reverts commit cfe7463fe2.

* Update README.md

* Update .gitignore

* update

* merge

* revert

---------

Co-authored-by: Manuel Schmid <manuel.schmid@odt.net>
2024-02-25 21:36:25 +01:00
MindOfMatter 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.

* add max loras config feature

* Update README.md

* Update .gitignore

* update

* merge

* revert

* refactor: rename default_loras_max_number to default_max_lora_number, validate config for int

* fix: add missing patch_all call and imports again

---------

Co-authored-by: Manuel Schmid <manuel.schmid@odt.net>
2024-02-25 21:12:26 +01:00
MindOfMatter 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.

* add lora enabler feature

* Update README.md

* Update .gitignore

* update

* merge

* revert changes

* revert

* feat: change width of LoRA columns

* refactor: rename lora_enable to lora_enabled, optimize code

---------

Co-authored-by: Manuel Schmid <manuel.schmid@odt.net>
2024-02-25 19:59:28 +01:00
Manuel Schmid b5f019fb62
fix: correctly create directory for path_outputs if not existing (#1668)
* correctly create directory for outputs if not existing

* feat: add make_directory parameter checks for list, extract make_directory to util
2024-02-25 18:41:43 +01:00
dooglewoogle ef1999c52c
feat: add ability to load checkpoints and loras from multiple locations (#1256)
* Add ability to load checkpoints and loras from multiple locations

* Found another location a default path is required

* feat: use array as default

---------

Co-authored-by: Manuel Schmid <manuel.schmid@odt.net>
2024-02-25 12:47:14 +01:00
Manuel Schmid 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
Manuel Schmid 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.

* introduce state for task skipping/stopping

* fix return parameters of stop_clicked

* code cleanup, do not disable skip/stop on stop_clicked

* reset last_stop when skipping for further processing

* fix: replace fcbh with ldm_patched

* fix: use currentTask instead of ctrls after merging upstream

* feat: extract attribute disable_preview

* feat: extract attribute adm_scaler_positive

* feat: extract attribute adm_scaler_negative

* feat: extract attribute adm_scaler_end

* feat: extract attribute adaptive_cfg

* feat: extract attribute sampler_name

* feat: extract attribute scheduler_name

* feat: extract attribute generate_image_grid

* feat: extract attribute overwrite_step

* feat: extract attribute overwrite_switch

* feat: extract attribute overwrite_width

* feat: extract attribute overwrite_height

* feat: extract attribute overwrite_vary_strength

* feat: extract attribute overwrite_upscale_strength

* feat: extract attribute mixing_image_prompt_and_vary_upscale

* feat: extract attribute mixing_image_prompt_and_inpaint

* feat: extract attribute debugging_cn_preprocessor

* feat: extract attribute skipping_cn_preprocessor

* feat: extract attribute canny_low_threshold

* feat: extract attribute canny_high_threshold

* feat: extract attribute refiner_swap_method

* feat: extract freeu_ctrls attributes

freeu_enabled, freeu_b1, freeu_b2, freeu_s1, freeu_s2

* 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

* wip: add TODOs

* chore: cleanup code

* feat: extract attribute controlnet_softness

* feat: extract remaining attributes, do not use globals in patch

* fix: resolve circular import, patch_all now in async_worker

* chore: cleanup pid code
2024-02-24 19:01:06 +01:00
Manuel Schmid a78f66ffb5
fix: sort with casefold, case insensitive
https://docs.python.org/3/library/stdtypes.html#str.casefold
2024-02-12 21:59:22 +01:00
Manuel Schmid 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
eddyizm 074b655dff
fix: implement output path argument (#2074)
* added function to check output path arg and override, other wise, use temp or fallback to config

* added function to check output path arg and override, other wise, use temp or fallback to config #2065

* Revert to 1bcbd650

* moved path output arg handling inside config start up

* Revert "added function to check output path arg and override, other wise, use temp or fallback to config"

This reverts commit fecb97b59c.

* Updated tag to uppercase

* updated docstring to standard double quotes.

Co-authored-by: Manuel Schmid <9307310+mashb1t@users.noreply.github.com>

* removed extra check on image log flag per feedback

* feat: update config_dict value when overriding path_outputs, change message

---------

Co-authored-by: Manuel Schmid <9307310+mashb1t@users.noreply.github.com>
Co-authored-by: Manuel Schmid <manuel.schmid@odt.net>
2024-02-11 13:04:06 +01:00
hisk2323 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
Evgenii c32b9bdc44
fix: replace regexp to support unicode chars (#1424) 2024-02-10 19:15:57 +01:00
Manuel Schmid 98ba1d5d47
fix: correctly sort files, display deepest dir level first (#1784) 2024-02-10 19:03:26 +01:00
V1sionVerse d1a450c581
Fixed mistakes in HTML generation (#2187)
Added <!DOCTYPE html> declaration
<img/> instead of <img></img>
<br/> instead of </br>
2024-02-10 17:50:41 +01:00
lllyasviel 1bcbd6501b fix config 2024-01-27 16:18:26 -08:00
lllyasviel 69ad1b3c24 advanced preset load
new model list

i

new candidates

add model fallback

allow disable preset download

Update anime.json

Update anime.json

Update config.py

Update anime.json

Update readme.md

Update default.json
2024-01-27 08:06:31 -08:00
Hunter-Houts ff2187efed Upgrade requirements_met function (#1955)
* Upgrade requirements_met function

* Removed extra import

* Using Requirements instead of Regex
2024-01-27 05:12:34 -08:00
rayleichenxi 80068a0cd7 [enhance]: use opencv to rewrite morphological_open(), achieve a 40x speed increase in morphological_open opporation, for inpanting images size smaller than 3k (#2016)
Co-authored-by: 雷晨曦 <leichenxi@qiyi.com>
2024-01-27 05:12:34 -08:00
Chris Rohrer f298ebca76
feat: adds preview overlay for styles (#1762)
* feat: adds preview overlay for styles

* fix: implement correct path resolution for all OS

solves issues for Windows

* fix: makes preview overlay also work with other languages

* feat: scale down images to 258x200, fix aspect ratio in css

reduces file size from 19,6MB to 3,4MB

* fix: adjust z-index to correctly overlay gradio border pulse when generating images

* update files

* version

---------

Co-authored-by: Manuel Schmid <9307310+mashb1t@users.noreply.github.com>
Co-authored-by: Manuel Schmid <manuel.schmid@odt.net>
Co-authored-by: lllyasviel <lyuminzhang@outlook.com>
2024-01-07 15:10:42 -08:00
lllyasviel e5af760db8 mask upload 2024-01-02 08:21:50 -08:00
xhoxye 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
lllyasviel 8e62a72a63
(requested) support AMD 8GB GPUs via Windows DirectML
this update is requested by users
2023-12-30 06:30:59 -08:00
lllyasviel 2f6ebbf876 some fix for previous PRs 2023-12-28 08:07:43 -08:00
御坂IO ad158450e3
fix to_clipboard from non-localhost access (#1576)
tested on edge(windows&android)
2023-12-28 07:54:59 -08:00
Manuel Schmid 48b1324a26
add default_max_image_number to config, use as maximum in default_image_number (#1616) 2023-12-28 07:48:30 -08:00
lllyasviel 7b5bced6c2
small url fix (#1551) 2023-12-22 00:20:09 -08:00
lllyasviel 81107298a8
minor fix (#1532) 2023-12-20 19:58:53 -08:00
lllyasviel 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
lllyasviel f308489440
Add Marc K3nt3L's styles
Thanks Marc K3nt3L !
2023-12-18 19:01:52 -08:00
Huy Nguyen 7a6b46f363
New Log System 2023-12-17 20:20:02 -08:00
lllyasviel 0e1aa8d084
better caster (#1480)
related to mps/rocm/cpu casting for fp16 and etc on clip
2023-12-17 17:09:15 -08:00
lllyasviel 1669370d2e
Refactor CLIP Vision 2023-12-17 00:13:51 -08:00
lllyasviel 67808d5ee5
fix all precision issues
We fixed number precision issues again. Now 2.1.849 will give 100% exactly same results as 2.1.824.
2023-12-16 19:54:05 -08:00
lllyasviel efb312d495
fix autocast (#1459) 2023-12-16 17:16:24 -08:00
lllyasviel 085bc3aeaa
revise caster 2023-12-16 16:58:46 -08:00
lllyasviel ec5dd950a2
Fix many precision problems
Many users reported that image quality is different from 2.1.824. We reviewed all codes and fixed several precision problems in 2.1.846.
2023-12-16 15:55:53 -08:00
lllyasviel 179bcb2c4e
Fix inpaint device problem in `--always-gpu` mode. (#1420)
2.1.841
2023-12-14 19:15:16 -08:00
lllyasviel 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
lllyasviel 5b99e3a1e4
2.1.839 2023-12-13 21:14:50 -08:00
lllyasviel df615d3781 fix some precision problems 2023-12-13 13:05:33 -08:00
lllyasviel f8e651a483 [2.1.831] Fooocus Describe 2023-12-12 19:34:18 -08:00
lllyasviel 9c3fb90df3 try fix cpu tree 2023-12-12 14:14:30 -08:00
lllyasviel 47441736ae maintain 2023-12-12 13:44:16 -08:00
AlexL 9cd3c06c6f
Make a simple table in html log output (#1286) 2023-12-12 13:33:28 -08:00
lllyasviel e8d88d3e25 2.1.826 2023-12-12 11:38:05 -08:00
oivasenk ec57c1fde0
Update private_logger.py (#1025)
Minor optimization of logs. Added lazy loading of images.
2023-11-24 01:31:20 -08:00
lllyasviel 3bc9ac88fd maintain 2023-11-23 13:46:50 -08:00
lllyasviel bd4d40203c ling 2023-11-21 10:16:45 -08:00