Neoki Ohae Style [Fluffy Ears Edition]版本v1.1 (ID: 73831)

A some what "dreamy" style good at making cute cat girls. Or sheep girls. Or dog girls. Or any type of animal eared girl really. Plus frills, lots of frills, dresses and fluffy stuff.
If you want the real undiluted diabeetus-inducing stuff free of mangled hands you can go support the artist here.

How to use
Prompt normally, even just "1girl" works. Tags to try is "chibi" and various cat girls tags like "animal ear fluff", "cat ears", "tail" etc. Usually you only need "animal ear fluff".
Another tag to try is "simple background" in negatives, all the images in the dataset are generally very detailed.

As of the 1.1 the LoRA has been trained on more than just catgirls and you can use the wildcard prompt below to generate random cute animal-eared girls.

Recommended LoRA strength is around 0.8 to 1. As of version 1.2 this LoRA should work well in models with realism mixed in like AOM2 without using "3D" and/or "realistic" in negatives.
Nearly all images in the dataset have the characters holding something, often food, so you might want to add "holding" and "food" to negatives if that causes problems with your model.

Don't forget to review and upload your own images, it's always fun to see what you're creating!
Like my LoRAs and want more? Please consider a small tip towards my electricity bill and further training >.<

Random Dynamic Prompt
1girl, solo,
{bat ears|
bear ears|
cat ears|
curled horns|
dog ears|
fox ears|
horns|
mouse ears|
rabbit ears|
sheep ears|
sheep horns|
squirrel ears|
wolf ears}

MISC
Trained on NAI. Dataset of nine images. for V1 and 25 images for V1.1.
All images are raw txt2img upscaled, no inpainting or helper embeddings used.

描述:

Trained on a more general dataset of gatcha like "character cards" images. Just like before this LoRA is good at general animal eared girls, frilly dresses and feel good fluff stuff

训练词语: