LOTM/COI LORA

About this version

Trained on IllustriousXL 1.0. I think it's a bit overfitted in some ways and may have issues with generating more than 1 character (2 is still possible depending on prompt).

Experimental version based on the old dataset as I had issues with training Illustrious models before. It is compatible with finetunes, but depends on the model. I'll update dataset and captions, with new characters, later.

Strength: 1

Trigger Words

amonlotm
audreyhall
forswall
gehrmansparrow
kleinmoretti
leonardmitchell
merlinhermes
algerwilson
azikdeath
azikeggers
derrickberg
ebrlotm
emlynwhite
evernightgoddess
lumianlee
medicilotm
mrfool
adamlotm
ccattleya
xioderecha
rosellegustav
bernadettegustav

Compatibility:

Works with models like 5th tail
Does not work with PonyXL models

Characters (18 total from official/fan art): Klein Moretti (+3 personas: Merlin Hermes, Gehrman Sparrow, Mr Fool), Audrey Hall, Fors Wall, Leonard Mitchell, Alger Wilson, Amon, Azik Eggers (past/present), Derrick Berg, EBR, Emlyn White, Lumian Lee, Evernight goddess, Medici, Adam, Cattleya, Xio Derecha, Roselle Gustav, Bernadette Gustav

Additional Features:

"Happy Birthday" image style from official images
Stylistic influence

Prompting:

Best format: trigger word, lotm, 1girl/1boy
Caution: May generate copyrighted content (to be fixed in future versions)

Generation Method:

Used ComfyUI (workflow: https://pastebin.com/GGEX27ce)

Note: Future updates will include improved captions and dataset images to address lessen overfitting.

LOTM [Illustrious] LORA (Lord of the Mysteries) - Illustrious v0.5