Trained on Tsubaki, 13 images.
An alternate version of the battlesuit Xenovia I posted, which is a better LoRA, in my opinion. I must confess that I'm not the most pleased with this one. It sometimes does not produce DxD season 2 or 3 Xenovia art style, and sometimes, it generates her with the school uniform, even though you did not prompt it. It's still much better than the SD or SDXL models, and it won't require more than 12 attempts to get a good result, but worse than the Xenovia battlesuit version.
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. It's a change from the previous SDXL and SD models.
LoRAs I used in generation: https://pixai.art/en/model/1839426804048327588
Thumbnail model: Tsubaki
