Age | Commit message (Collapse) | Author |
|
|
|
This algorithm plots a bunch of points of interest on the source
image and averages their locations to find a center.
Most points come from OpenCV. One point comes from an
entropy model. OpenCV points account for 50% of the weight and the
entropy based point is the other 50%.
The center of all weighted points is calculated and a bounding box
is drawn as close to centered over that point as possible.
|
|
|
|
assoicated -> associated
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
checkpoints that have weird cond_stage_model layer names)
|
|
|
|
|
|
|
|
|
|
|
|
utf-8-bom for better compatibility for some programs
|
|
have launch.py examine both COMMANDLINE_ARGS as well as argv for its arguments
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Don't eat colons in booru tags
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
that one could allow access to /sdapi/ but not the webui.
|
|
both.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Added possibility to set the theme (light or dark)
|
|
Launch the UI in dark mode with the --dark-mode switch
|
|
|
|
|