Trained on Tsubaki, 13 images.
DiT V1 annoyance: Another LoRA I'm bringing to DiT V1. This time, it's one of the Murasaki twins, Kaori. AI prefers to generate her choker black. Black choker is Kaoru's; that's annoying. I used "white silver spiky choker", maybe modify "choker" to "white choker" too, and it should help. I don't usually change the original prompts, as I don't want to break it.
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
