Updated: Sep 9, 2026
characterDownload
1 variant available
fp16 SafeTensor
TianaVonReyl_Anima_v1.safetensors
Half precision, best balance ⢠63.23 MB
Verified: 2 days ago
670 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
10 1 2 3 4 5 6 7 8 9
(13)
Sep 9, 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
Tiana von Reyl Character LoRA
Bring Tiana von Reyl to life with this character LoRA trained from uncolored manga artwork from the manga From Leveling Up the Hero to Leveling Up a Nation, using my refined training process for Anima models.
The dataset was carefully curated to capture Tiana's distinctive appearance while providing variation in poses, expressions, angles, and settings. Particular attention was given to Tiana's physical appearance and recognizable features, including her blonde hair, long braided ponytail, blue eyes, red glasses, pink ribbon, and distinctive hairstyle, with the goal of preserving her identity while allowing the character to remain flexible across different generations.
Source Material & Training
The source dataset was built primarily from uncolored manga panels, with the images carefully selected and prepared for character training.
Rather than relying on fully rendered promotional artwork or a collection of colored illustrations, the dataset focuses on the manga's original line art and shading. This provides a strong foundation for learning Tiana's recognizable physical characteristics while allowing the trained LoRA to generate her in fully colored illustrations and a variety of visual situations.
The dataset was manually curated with an emphasis on character identity, feature consistency, and visual variation. Different poses, expressions, camera angles, and environments were included to help prevent the character from becoming overly associated with any particular composition or scene.
The final model was trained using my updated Anima-model training process, incorporating the lessons learned from previous character LoRAs and continued refinement of my dataset preparation and training workflow.
Features
Character-focused LoRA for Tiana von Reyl
Character from From Leveling Up the Hero to Leveling Up a Nation
Dataset sourced primarily from uncolored manga panels
Focused on preserving Tiana's physical appearance and distinctive features
Blonde hair and long braided ponytail
Blue eyes and red glasses
Pink ribbon and distinctive hairstyle
Trained using my updated Anima-model training process
Supports a variety of poses, expressions, and environments
Designed to preserve Tiana's recognizable appearance
Works with different outfits
Manually curated dataset
This model is part of my growing collection of character and outfit LoRAs, created using careful dataset curation, experimentation, and iterative training refinement.
Have fun with Tiana! š
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!
ā Daraco
NOTE: ArmetDaraco | Profile | Arc en Ciel is my official model list. The Bots are scraping these, so if you are finding them on any other site, they are reposted (hopefully with proper credit). So if you want to stay updated and support me in future releases, please follow me on Arc en Ciel!!

