This is a lora I trained to depict Sakura from part 1 of Naruto.

The trigger word is "Sakura". After that you should generally lead your prompt with "an anime screenshot of..." It can do long or short hair.

The training was done with screenshots of the size 640x480, but it works at other resolutions and aspect ratios as well. I find the sweet spot to be 1216x832.

This lora was not meant to replicate the sharpness and high quality of modern anime/anime artwork. It was designed to create reasonably believable part one screenshots.

Please let me know if you have an tips or suggestions and consider donating buzz if you enjoy my work.