Download
2 variants available
SafeTensor
320 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
20 1 2 3 4 5 6 7 8 9
(4)
Sep 20, 2026
This is my first attempt with Krea2 LoRA

680 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
2450 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
4.3K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
This LoRA is designed to generate Galen, the protagonist from the videogame Ninety-Nine Nights II.
I am still learning how to train LoRAs for Anima models, so feedback is highly appreciated!
Recommended Weight:
0.8 - 1.0(0.9 often yields the best results depending on your checkpoint).
Base Character:galenn, silver hair, short hair, swept back hair, blue eyes, stubble, scar
Default Outfit (Optional):
Add these tags if you want to generate his signature armor:dark plate armor, ornate collar, plate armor, ornate armor, red emblem on chest, pauldron, bare shoulder, armored arm, greaves, boots
This is my very first LoRA trained for Krea 2, so it might not be absolutely perfect, but I'm really happy with how it turned out!
How to use:
Trigger Word:
[galenn](Use this phrase in your prompt to activate the effect).Recommended Weights:
0.8 - 1.2(Adjust based on your needs).
Krea (V1): High flexibility / Great for custom outfits & styles. Less baked.Krea 2: High accuracy / Trained with more steps for a stronger likeness to Galen. May leak flexibility when changing clothes or styles.
Please check the gallery images to see the exact prompts and settings I used to get an idea of how it behaves. I'd love to see your generations, so feel free to share your results in the comments!
Este LoRA esta diseñado para generar imagenes del Perosnaje Galen del Ninety-Nine Nights II.
Sigo aprendiendo en como entrenar LoRAs en Anima.
Lo recomendado para el LoRA: 0.8 - 1, Puede variar los resultados dependiendo del Checkpoint, a veces 0.9 es un buen balance.
Training Base Models
This LoRA was trained using the following base models:
anima-base-v1.0
illustriousXL20_v20
krea2_raw_bf16

