Ingrid — a gorgeous young Swedish woman with long straight platinum blonde hair, icy blue eyes, an angular face with sharp cheekbones, very fair porcelain skin, and a tall strong athletic build.
This LoRA captures Ingrid's face and identity for consistent renders across poses, outfits, and scenes. Retrained on the Krea 2 V30 base (RawRealDark_v2_V30) from a fresh 40-image identity set for sharper identity lock and natural skin texture with visible pores.
Trigger word: ingrid_face
Recommended strength: 0.6 (0.5–0.7 also works). Use 0.3–0.5 if she drifts or you want a lighter touch.
Works best with: Krea 2 base models. Photorealistic style, natural lighting.
Example prompt:
ingrid_face, a gorgeous young Swedish woman with long straight platinum blonde hair, icy blue eyes, sharp cheekbones, very fair porcelain skin, tall athletic build, wearing a dark leather Norse warrior tunic with leather shoulder guards, holding a bearded axe and a round wooden shield, fierce determined expression, misty fjord at dusk behind her, full body, photorealistic, natural skin texture
Negative prompt tips: avoid "bright" before eye colour (can cause glowing eyes). She is fair-skinned — negate olive/golden/tan skin or she warms up.
This is a fictional character. All images are AI-generated.
A matched slim-body LoRA is available on this version for a leaner silhouette.
⭐ Enjoying Ingrid? A rating + 👍 on the previews makes a real difference to an indie creator. Tack, and thanks for the support!
Description
v1.2 — V30 retrain.
What changed: retrained from scratch on the Krea 2 V30 base (RawRealDark_v2_V30) using a fresh 40-image identity set for sharper identity lock and more natural skin texture with visible pores. Replaces the v1.1 blend-trained face LoRA.
Training: 16 epochs / DIM32 alpha32 on RawRealDark_v2_V30 — 40 images → 640 steps. Resolution 1536x2048, batch 1. Final loss 0.0246. Base: Krea 2.
Same trigger word (ingrid_face) — drop-in replacement for v1.1, no prompt changes needed.
Recommended strength: 0.6.
Companion: ingrid_slim_body.safetensors is attached on this version as an Enhancement LoRA (face @ 0.6 + slim body @ 0.8 on booty/back shots).




