DiT.1 and XL versions are available. Their respective preview artworks (if any) and trigger words (if differs) can be inspected separately via selecting the versions at the top, below the title (on desktop browser, need to open a full separate page of this LoRA first to see them)
Generates most consistently on its corresponding base models, "Hoshino" (XL) and "Tsubaki" (DiT). On other models, it may have severe artifacts and/or discrepancies from the oiginal appearance image, unfortunately
The model is compiled through collective image from a conjunction of many pictures of slightly different executions (more realistic vs. more cartoonish/minimalistic vs. more abstract, and such) in representations from a variety of different artists, so if you like to, want to settle on an any specific one of all them, you may need to use the "Variations" function, set the task seed, adjust trigger words in the prompt accordingly, etc.
