Serena Ijiyuuin / 伊集院セレナ | Vampire (2011) / ヴァンパイア(2011) | DiT V1/V2

Trained on Tsubaki, 13 images.

Just don't ask her to suck you dry. 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