Experimental lora-tuning mix. May not be to your taste. Please don't use commercially but feel free to remix. Negative embeddings not necessary for quality but might be helpful.
This model is built on top of NoobAI-XL. Specifically, it uses Better Days. Illustrious v0.1 as a base, or even more specifically a re-merged version of it called betterDaysIllustriousXL_V01ItercompPerpCyberillustfixPerpWeightedSum05 which consists of a perpendicular merge with two stabilizing models. If you're really interested in how it performs without the lora merge, you can find it here or here, with some some x/y comparison pics here.