Age | Commit message (Collapse) | Author |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
have launch.py examine both COMMANDLINE_ARGS as well as argv for its arguments
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Added possibility to set the theme (light or dark)
|
|
Launch the UI in dark mode with the --dark-mode switch
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
embedding before the generation using text
|
|
|
|
|
|
|
|
switching time reduced from ~1500ms to ~280ms
|
|
rather than gradio input
|
|
|
|
load models to VRM instead of RAM (for machines which have bigger VRM than RAM such as free Google Colab server)
|
|
|
|
* Add 'interrogate' and 'all' choices to --use-cpu
* Change type for --use-cpu argument to str.lower, so that choices are case insensitive
|
|
|
|
|
|
|
|
|
|
Interrogate: add option to include ranks in output
|
|
|