I use it with AnythingV3 and this as a base prompt:
1girl, short hair, blue neck ribbon, two side up, red hair ribbon, hime cut bangs, swept bangs, parted bangs, blush, yellow cardigan, sleeves past wrists, brown hair, black socks, long sleeves, sailor collar, dark blue sailor collar, dark blue eyes
I also use the ft-MSE VAE from here https://huggingface.co/stabilityai/sd-vae-ft-mse-original but it's mostly for more saturation.
Vivy LoRA: https://files.catbox.moe/yq5xmx.safetensors
The Vivy LoRA is trained on this album: https://imgur.com/gallery/SLxcxmJ and it's not really doing much. I just made it to make some close up Vivy eyes.
LoRA on civitai
Rune LoRA: https://files.catbox.moe/sf5meh.safetensors
here's a link to the loRA itself, with the caveats that i don't really know what i'm doing when it comes to training (but it seems to work), the base model is abyssorangemix2_sfw so it should work best with that, it should help to specify
in the prompts because that's what they're tagged as on danbooru where i scraped the pictures from, and i think you have to use the 'additional networks' a1111 extension instead of the built in loRA support unless the incompatibility bug with the latest training scripts is finally fixed