Sign In

Mia de Jong - Sharp-Tongued Dutch Police Officer

Download

1 variant available

fp16 SafeTensor

qtrvl7_krea2_000001400.safetensors

Half precision, best balance • 218 MB

Verified:

Type
LoRA
Stats

29

Reviews

No reviews yet

Published

Nov 18, 2026

Base Model
Training
Steps: 1,400
Usage Tips
Strength: 0.9
Hash
AutoV2A015E7E291
Trigger Words
qtrvl7 woman

Krea 2 is licensed under the Krea 2 Community License Agreement. For more information, visit https://krea.ai/krea-2-licensing.

black-velvet-gown-opera-staircase-chandelier_01_00001_.png

She already decided you're wrong. She's just waiting for you to finish.

Mia de Jong, an original fictional character: a twenty-five-year-old Dutch police officer with a cutting tongue, a short temper and a love of action, who has never doubted she is the best in the room. Straight copper-red hair with a short side-swept fringe, fair freckled skin, hazel-brown eyes and red lipstick. Trained on Krea 2 Raw from synthetic images of a made-up character.

Trigger: qtrvl7 woman

  • The trigger gives her face, her copper hair with the side-swept fringe, her freckles and her red lipstick.
  • Write out any outfit you want. She was trained in a Dutch politie uniform (white shirt, navy tie and trousers), a patrol look with a navy beret and black leather jacket, training clothes, an arrest-team kit (navy turtleneck, black AT/POLITIE plate carrier, utility belt, gloves, blue wraparound sunglasses, jeans and combat boots) and eight everyday outfits, all described in plain words, so everything stays promptable.
  • Example: qtrvl7 woman in a navy turtleneck under a black plate carrier with white AT and POLITIE patches, black tactical gloves, hair in a ponytail.
  • Hair is promptable: "hair loose" or "hair in a ponytail".
  • Expressions are promptable: stern, scowling, dismissive, smirking, laughing, surprised, sad.
  • Weight 0.8–1.0 (0.9 is a good default).
  • Known quirk: "a woman with copper-red hair, a side-swept fringe and red lipstick" leans toward her even without the trigger, so describe a different person in full when you want someone else.

The dataset for this LoRA was generated with GPT Image.

All showcase images are made with this LoRA on a Krea 2 realism checkpoint, 8 steps, CFG 1.

If you like my work, leave a comment, like, or whatever! It'll motivate me to make more and share more. Thank you!