Android 18 / 人造人間18号 | Dragon Ball Super / ドラゴンボール超 | DiT V1/V2

Trained on Tsubaki, 12 images.

DiT V3 version: https://pixai.art/en/model/2057368420941199799/2057368422115604930

Applies to DiT V2 only: If you want to generate her in the magenta tracksuit, prepare to copy prompts for the outfit from the images you can see below. I don't hide prompts, so you can copy them from me and adjust them as you wish. At the moment, DiT V2 doesn't use "AI prompts"; basically, AI makes your prompts sound more descriptive.

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