Trained on Tsubaki, 13 images.
Applies for DiT V1: tip right off the bat: Have ready the prompt "male" because when you try to generate him with other outfits, you get female. If you want him topless, and he doesn't generate with nipples, use the " male nipples" prompt too. Otherwise, it's fine. Arashi has a lot of scars, but because they aren't shown that often, I decided not to train the LoRA off of these images.
I only used Tsubaki to generate the images, but I think you can use other DiT models.
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.
