Download
1 variant available
fp16 SafeTensor
Yumi_Suikoden_III_Anima.safetensors
Half precision, best balance • 63.24 MB
Verified: 13 days ago
330 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
20 1 2 3 4 5 6 7 8 9
10 1 2 3 4 5 6 7 8 9
(4)
Aug 30, 2026

5.7K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
4750 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
3.3K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
License:
AnimaThe 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
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!!

