Version 1.8L (for loras!)
ALL the 2.1 based trained LORAS added in following the same blend schedule described before. (there is a difference between the SD1.5 versions fyi!)
What the model differences are:
1.8 = (the sloppy fun drunk) broad artistic vivid. Not scared to spill the wine while tipsy painting. Oh I made a Salvator Mundi? Cool.
Example: The flower rose prompts. Vivid & vibrant.
1.8L = Less drunk with a sharpened crayon. Dinosaurs? ya gotchya, I won't make them as gross (Thanks dino lora's!)
What the 1.8L LOSES > A chunk of it's upbeat sloppy creativity (flowers for instance are a darker shadier kind of cool.) It grew up a bit.
Examples: added samplers and examples to gallery for you to see yourself.
Does this beat any lora by itself? NO. A trained lora on only dinos for example will be better if you are only making dinos 24/7.
What this does is sharpen the pencils in the entire artist box. It makes it shape up a bit, mature - still a general model! But pulls it away from the original direction.
Think of those people who cook naturally then go to chef school ~ but that ruins their food a bit when they shape up to start cooking classically. You miss the older sloppier chef friend you had who didn't care about a four hundred dollar spice. haha ;)
Now you can decide what kind of crazy artistic wingman you want. =)
Notes: Future updates will continue down this path. Split + SplitLORA
