A new character for the Cast. Dark hair, warm mediterranean features, that easy everyday look — versatile across daylight, urban night, and quiet indoor scenes.
Fourth Krea2 character in the Cast.
Specs
Trigger word:
K_Gu14_KSCBase model: Krea2
Recommended weight: 1.0 — sweet spot
Working range: 0.8 → 1.2
Notes
Stress-tested across a wide range of prompts and contexts — character holds, flexibility is there.
All preview images here were generated with Guia alone, no style LoRA stacked. What you see is the LoRA on its own.
Pairs naturally with the ShinobiSat Krea2 Workflow — same pipeline, tested together.
If you cook something nice with her, drop it in the gallery.
Guia is the ninth drop of the ShinobiSat Cast — a growing series of photoreal character LoRAs, now across multiple base models. More coming.
— ShinobiSat
Description
Trigger word:
K_Gu14_KSCBase model: Krea2
Recommended weight: 1.2 — sweet spot - Based on the base model used, I find 1.1 to be better.
Working range: 0.9 → 1.4
This version fixes the checkerboard artifacts that appeared in images generated with v1.
I believe the cause was the training dataset, which has a deliberate, specific grain. During training that grain was apparently over-learned, which produced the checkerboard pattern. I retrained the LoRA on the same dataset with a gentler training run to prevent this.
I no longer see the artifacts in my tests, and the LoRA stays faithful to v1. It may need a higher strength, around 1.1-1.2: at 1.0 the face is faithful in most cases, but the nose piercing is sometimes missing, while at 1.2 the likeness is at its best and the piercing shows up in over 90% of generations.
I hope you like this new version, and I'd appreciate any feedback or suggestions to improve it further. Thanks!