Trained on Tsubaki, 11 images.
Another LoRA I bring to DiT V1. To be completely honest, she's probably my worst LoRA for DiT V1, in terms of fingers, quite inconsistent compared to other LoRAs.
Same like Lizel, she doesn't generate quite well in DiT V2, I recommend using older versions.
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
