* 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>
* 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
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
* 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>
* 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>
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
* 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>
* 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
* 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
* 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.
Now the GPT will try to (1) use more aligned formatting of commas, (2) a bit more dynamic in word choice, (3) avoid duplication like “detail, detail, detail, detail”
MindOfMatter
Manuel Schmid
dooglewoogle
Manuel Schmid
eddyizm
hisk2323
Evgenii
V1sionVerse
lllyasviel
Hunter-Houts
rayleichenxi
Chris Rohrer
xhoxye
御坂IO
Huy Nguyen
AlexL
oivasenk