Inspired by 1to3fall5's Don't Starve Together LoRA, this LoRA attempts to generate the style of Invisible Inc. on portraits.
It seems to work fairly well with SDXL Base with few Refiner steps (I did 24:1) at strength 0.9. It does like to duplicate lapels, and at some aspect ratios has a tendency to either duplicate mouths/noses or add subjects, though this is usually easy to correct by changing the aspect ratio. It has very limited ability to generate objects in the style beyond clothing and faces.
Data collected from Invisible, Inc. Wiki.
1. Dieses Modell dient nur Lernzwecken. Urheber- und Auslegungsrechte liegen beim Originalautor.
2. Bist du der Originalautor eines Modells, kontaktiere uns bitte zur Authentifizierung über unsere offiziellen Kanäle. Wir schützen die Rechte aller Schöpfer. Hier klicken, um es zu verifizieren.
