Sign In

Kanako Urashima (Love Hina)

89

Updated: Aug 31, 2026

characterlove hinaanimegirls

Download

1 variant available

bf16 SafeTensor

Kanako_Urashima_(Love_Hina)Ani.safetensors

BF16, good balance • 33.14 MB

Verified:

Type
LoRA
Stats

103

0

Reviews
Published

Aug 31, 2026

Base Model

Anima

Training
Epochs: 12
Usage Tips
Strength: 1
Hash
AutoV2
BA43B17614
Trigger Words
uraskanako4ni, black hair, long hair, blunt bangs, sidelocks, ponytail, ahoge, brown eyes, hair ribbon, neck ribbon, white vest, black dress, sleeveless, long dress, open dress, shorts under dress, goth fashion, brown footwear, boots
default creator card background decoration
Followers - 1152

1.2K

Likes - 3514

3.5K

TheAlly's Granny Grippers!

License:

Anima

The Anima Model is licensed by CircleStone Labs LLC. Copyright CircleStone Labs LLC. IN NO EVENT SHALL CIRCLESTONE LABS LLC BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

Built on NVIDIA Cosmos

Kanako Urashima is the step sister of the main character Keitaro Urashima. She is introduced in the short OVA Love Hina: Again. A conflicted and headstrong girl with unresolved feelings for her step brother, she declares herself Narusegawa's rival and the one who truly loves her brother.

I like her design and the gothic look, but the brother-sister thing is somewhat off putting for me personally. Nevertheless, doesn't mean she doesn't deserve a lora of her own. :)

Usage notes for different versions:

Anima: Works on strength 1. Updated dataset with several anime screenshots. If the various ribbons she wears generate in wrong colors just specify the color within the tag.
Illustrious: Works on strength 1. Somewhat updated dataset from PonyXL as few images were generated with the PonyXL lora and added to the training data of the illustrious lora.
PonyXL: Works on strength 1. Needless to say, a lot more accurate than the SD 1.5 version. Not much else to say.
SD 1.5: Use strengths 0.9 - 1 as they work best in my opinion. Just lowering down to 0.8 can cause the lora to lose a lot of accuracy.

Hope you like the lora! :)