Myrmicus and Tamra's Style Mix

so.... following @Silvana_'s idea of combining my style with hers,

which gave us this gem, here : https://civarchive.com/models/2732862/tamra-and-silvanas-style-mix

then the idea to do it again with @Myrmicus's style and hers,

which gave us this one : https://civarchive.com/models/2800552/myrmicus-and-silvanas-style-mix

the only logical thing to do next was to mix Myrmicus's style with mine,

and now here we are.

How?

It was trained using 2 different trigger tags @tamra and @myrmicus

60 images of each style, 4 types of tagging per image.

• 120 just tags

• 120 natural language captions

• 120 both

• 120 just the trigger tags

all combined into one big dataset.

Why?

BECAUSE OF SILVANA and Myrmicus, go ask them, not me XD

Results?

Well i'd say "Judge by yourself, what do you think", but in truth, it's not terrible if i had to say so myself.
Yes, i hear you (fictional character in my head) ! It can give some weird results, sometimes... try using only 1 of the tags! or change the order you use them in!
use one twice!!!! Who knows what it will do !? Play with it, make it your own ! And above all else, have fun with it !

how to use

Mostly, surely, like any Anima Lora

i would suggest tho, to use er_sde as the sampler
maybe around 3 to 4.5 CFG and around 30 steps

but whatever works for you already would surely work too ^^