Trained on Tsubaki, 16 images.
Another LoRA I'm bringing to DiT V1. Her battlesuit does not generate as accurately as I would like, but it's fine. I think it's better compared to SDXL. Some details I should also mention: In her battlesuit, she generated with more cloth than she wears in anime, I used " cleavage and it removed quite a bit of cloth. How does it work? No idea. Also, for some reason, she sometimes generates with tanned skin, so if that happens to you, use "white skin" prompt. Otherwise, I think it's all.
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.
LoRAs I used in generation: https://pixai.art/en/model/1839426804048327588
Thumbnail model: Tsubaki
