Sign In

Elena (Star Ocean 6)

73

Download

1 variant available

bf16 SafeTensor

Elena_(Star_Ocean_6)Ani.safetensors

BF16, good balance • 33.14 MB

Verified:

Type
LoRA
Stats

92

0

Reviews
Published

Sep 17, 2026

Base Model

Anima

Training
Epochs: 12
Usage Tips
Strength: 1
Hash
AutoV2
49198EDE00
Trigger Words
elenaso6ani, blonde hair, long hair, blue eyes, high collar, yellow shirt, sleeveless, shoulder armor, chest harness, fingerless gloves, partially unzipped, zipper, cleavage cutout, cleavage, navel, multiple belts, buckle, thong straps, leg belt, pantaboots, black legwear, heels
default creator card background decoration
Followers - 1206

1.2K

Likes - 3777

3.8K

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

Elena (or Elena E-014297) is a humanoid android from Star Ocean 6. Apparently her looks are designed to "avoid inciting feelings of discomfort". She functions as the calm and collected first officer of the merchant vessel Ydas, and she is also Raymond Lawrence's second-in-command.

Usage notes for different versions:

Anima: Works with strength 1. Her outfit has a lot of straps and belts and her legwear is tagged as "pantaboots", an obscure booru tag that's relatively rarely used. Natural language can help in generating her outfit in more accurate detail to some extent.
PonyXL: Two versions available. V1: Due to poor training & low quality dataset, the lora will most likely produce low quality hands. "detailed 3d" prompt gives 3d-styled, decent hands most of the time, but "source_anime" will most likely produce hands that need inpainting. Lowering lora weight to 0.8 and increasing the character prompt weight ("elena_so6") can somewhat combat the poor hand quality. V2: Lora should deal better with generating hands. See comparison pictures of V1 versus V2.
SD 1.5: Works best with strengths 0.5 - 0.6. Higher strengths can cause issues when generating hands. Lora is tested mainly on 2d checkpoints, but the dataset has quite a bit of material from in-game cut scenes, so 3d and realistic models should handle the Lora decently well.

Hope you like the lora! :)