Trained on Tsubaki, 11 images.
One of the LoRAs I tried to train before, but failed. This was the last LoRA I was not able to train. Now, it is fully functional. DiT V1 really is superior by a mile. 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
