Sign In

Yumi (Suikoden 3)

2

Download

1 variant available

fp16 SafeTensor

Yumi_Suikoden_III_Anima.safetensors

Half precision, best balance • 63.24 MB

Verified:

Type
LoRA
Stats

33

2

1

Reviews
Published

Aug 30, 2026

Base Model

Anima

Hash
AutoV2
023220AABC
Trigger Words
yumisui,
brown hair, brown eyes,asymmetrical bangs,long hair,
brown hairband, green dress, short sleeves,brown gloves, knee boots, brown footwear, fur trim,
default creator card background decoration
Reactions - 5727

5.7K

Followers - 475

475

Likes - 3292

3.3K

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

2108002.png

Yumi Character LoRA

Bring Yumi to life with this character LoRA, directly ported from my previous NoobAI-based LoRA for use with Anima models.

This version is a straightforward conversion of the original model and uses the older dataset and training approach from the original NoobAI release. Unlike my newer Anima character LoRAs, this dataset was not rebuilt or curated using my updated workflow, so the tagging, image selection, and overall dataset structure may not be as refined as my more recent models.

The goal with this release is primarily to make the existing Yumisui LoRA available for Anima, while preserving the character and behavior of the original NoobAI version as closely as possible.

Features

  • Character-focused LoRA for Yumi

  • Direct port from my original NoobAI LoRA

  • Adapted for use with Anima models

  • Uses the original, older dataset

  • Uses the original dataset tagging and training approach

  • Supports different poses, expressions, environments, and outfits

  • Designed to preserve Yumi's recognizable appearance

  • This version has not been processed through my updated Anima training workflow

Future Update

I intend to revisit Yumi in the future and create an updated version using my newer Anima-model training workflow.

That future version will use a newly curated dataset with improved image selection, tagging, and training techniques developed through my more recent character LoRAs. The goal will be to improve character consistency and flexibility while taking advantage of what I've learned from my newer training process.

For now, this release is simply a way to bring the existing Yumisui LoRA over to Anima without waiting for the full rebuild.

Have fun with Yumi! 💚

If you enjoy this model, please consider leaving a rating or sharing your generations. Seeing what everyone creates is one of the best parts of releasing these projects.

Enjoy and Good Luck!

- Daraco


NOTE: ArmetDaraco | Profile | Arc en Ciel Is my official model list. The Bots are scraping these so if you are finding then on any other site, they are reposted (Hopfully with proper credit). So if you want to stay updated and support me in future releases, please follow me on Arc en Ciel!!