If you like the LoRa, please feel free to share your generated images here and leave a review (or at least a rating) for the sake of motivation and stuff ;D

For usage guidance, look into the About this version box for more information and click on Show more to get all trigger words and combinations (The trigger words in the Details box are a pain to manage).

Please contact me here on civitAi or on Twitter if you want to provide the LoRa in a generation service.

Please remember that this is currently a beta release...

About

I like the original Light Novel a lot more than the anime to be honest, the anime has just too many continuity errors for everything that is not relevant to the main character, but that is pretty much always the case with anime based on a Light Novel or Manga, the best they can do is get on the same level as the source... But whatever. Currently watching the 2nd season and its fun to watch ^^

Training

Well, the airtime of Yuna's bear costume is not evenly distributed. Most of the time she wears the black bear costume, followed by a huge gap of the white costume...

Unlike in the light novel, Yuna only occasionally takes off the hood of the costume, which is reflected in the training data, I tried to make the most of the few occasions when she is not wearing the costume at all, but well, in season 1 it happens not too often, and in season 2 it happens more often (In the next episode, she will definitely have some shots without the costume (and I will probably create a new LoRa version then ^^)). I ended up with 37 pictures for training.