I revised some training methods and released a V2. This one is miles ahead in terms of quality compared to V1 :)
Since all these SD3 shenanigans don't seem to find a satisfying end, and people asked for some Pony Loras. Let's give it a try!
As always, keep in mind: I'll try to use the absolute most basic prompt in my samples, so you can see the baseline that's possible (and I absolutely suck at prompting).
Tell me what you think and have fun!
Description
FAQ
Comments (6)
so badass, another one I'd really love to see for flux!
Yiay, I found my old dataset. Enjoy!
@CrunchyBanana seems like it baked in the face as well
@FrenzyX there are no faces in the dataset as far as I can see. Works perfectly fine with character LoRAs for me.
The Seeds are all within like 20 steps so maybe that's why the face are kinda similar in the samples
@CrunchyBanana alright, I'll give it a shot
@CrunchyBanana banana, my hero.













