What if I've tried to increase the prompt adherence in Illustrious v0.1 and its siblings? It's only a test though, because I'm not entirely sure if I did it correctly. :)
Left image - original checkpoint, right image - modified checkpoint. It seems the 'characteristics' of the original remain in the modified model, but prompt adherence is better for the most part.
Another observation - VAE inclusion gets 'reset', the resulting checkpoint doesn't have it.
The great merge, ANGRA Illustrious checkpoint, is also a very nice field for experimenting! It already has nice CLIP capable of understanding complex stuff, and this try of mine just changes the outcome a bit, especially with the nasty derelict bedroom. :)
This model is really good on his own, and the fact that it can simply try fitting multiple objects into portrait image is noteworthy!
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.
