Sign In
homemodelsimagesvideos3D Modelsarticlescomicsbountieschallengesupdatesshop

Nina Deforges (Star Ocean 6)

1.1k

Updated: Aug 23, 2026

characterstar oceangame character

Download

1 variant available

bf16 SafeTensor

Nina_Deforges_(Star_Ocean_6)Ani.safetensors

BF16, good balance • 16.63 MB

Verified:

Type
LoRA
Stats

56

1

1

Reviews

(10)

Published

Aug 23, 2026

Base Model

Anima

Training
Epochs: 12
Usage Tips
Strength: 1
Hash
AutoV2
A733546243
Trigger Words
nidefor4ni, short hair, brown hair, green eyes, hairband, hairclip, choker, necklace, blue vest, open vest, pink top, cross-laced top, cleavage, green undershirt, green sleeves, shoulder cutout, long sleeves, wide sleeves, fingerless gloves, navel, belt, belt pouch, short shorts, thighhighs, single garter strap, thigh boots, toeless footwear
default creator card background decoration
Followers - 1104

1.1K

Likes - 3344

3.3K

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

00051-1158610185.png

Nina Deforges, the dedicated healer girl of Star Ocean 6: The Divine Force. Personally I always liked her look, reminds me of that one Atelier girl with the thighs that internet ever tires of. :)

Most of the dataset in all the versions I've trained consists of a mixture of fan art and in-game screenshots.

Usage notes for different versions:

Anima: Works on strength 1. The outfit is quite detailed but should generate properly with just the tags, although the crisscross pattern on her top below her collarbones didn't get picked up in the training, so it's not 100% accurate.
Illustrious: Works on strength 1. The color of her shorts isn't completely consistent so prompting for "green short shorts" can help.
PonyXL: Works on strength 1. Some of the dataset consists of images from the old SD 1.5 lora with some img2img shenanigans to help with the quality. Unfortunately the lora doesn't quite capture her look as well as illustrious and Anima.
SD 1.5: Works well from 0.5 to 1 Strength, although the lower strength values tend to miss some details of the clothing (the thighhighs in particular). Did some testing with 3d and realistic models with this one, as the training data contains some 3d model pictures (well, in-game screenshots), and it seems to work decently on those as well.

Hope you like the lora! :)