Trained on Tsubaki, 11 images.
The number of her family techniques probably rivals the Kamasutra. I didn't do her armour accurately because it would be a pain in the butt, and I prefer using unique images over similar or identical ones, if possible. So yeah, I reimagined her armour a bit; it's a trade-off for more accurate body details, like heterochromia, lipstick, and horns, which eat up the letter limit quite a bit. Hope you enjoy.
I use Euler A. 28 steps. Because the results are pretty good, I think you can generate 3 images in parallel, and you will still be fine. Unlike SDXL, DiT is pretty consistent from my initial experience. Of course, if you demand a lot of detail, then maybe go cheap first.
I use 3, 4.5 and 6CFG. 0.7 Rescale CFG, same as every DiT V1 LoRAs I use.
Thumbnail model: Tsubaki
