This LoRA was trained on 21 handpicked images from gelbooru, zerochan, and pixiv with Anything v4.5. In this version, I reduced the number of fanart and added more screenshots from the anime into the dataset. This LoRA might be a little overcooked, but I think that its way better than the previous version.

To use this LoRA, include the trigger word shikimoriMicchon at a weight of around 0.75-0.85. No other descriptive words should be necessary! Consider using at a weight of 0.6-0.7 when mixing with other LoRAs.

To generate her school uniform, include the tags school uniform, black sweater, white shirt, red neck ribbon, and grey skirt with hair ribbon added to the negative prompts.
To generate her swimsuit, include the tags black crop top, cleavage, and denim shorts.

Version 1

This LoRA was trained on 19 handpicked images from gelbooru, zerochan, and pixiv with Anything v4.5.

To use this LoRA, include the trigger word shikimoriMicchon at a weight of around 0.75-1. Adding descriptive words like blue eyes and long hair should also help bring out the character's features.

To generate her school uniform, include the tags school uniform, white shirt, black sweater, neck ribbon, and grey skirt.
To generate her swimsuit, include the tags black crop top, collarbone, navel, and short shorts.

I'm looking forward to see what you all come up with. Be sure to leave feedback as comments and reviews!