Premium character LoRAs
Original synthetic characters, bundles and AI tools are in my shop:
Join the community on Discord: https://discord.gg/nB79wRNtMT
Chicks Wearing Chucks
A concept LoRA for Krea 2 focused on women in classic canvas sneakers: high-top or low-top, rubber toe caps and white laces, with shorts, skirts, socks, topless or nude. It gives an amateur photo look.
Usage
Start with the trigger word ChucksRK, then describe the sneakers precisely (high or low top, color, worn or new, laces, socks or bare ankles) without naming any brand, what else she wears or that she is topless or nude, the pose (sitting, legs up, from below), the framing and the place, and end with the light. Showing the feet in frame and naming the rubber toe caps brings out the effect the most.
ChucksRK, Photograph of a woman with <hair> in <white / red> high-top canvas sneakers with rubber toe caps and white laces, <denim shorts / topless>, <sitting with her legs up> on a <couch>. The lighting is <light>.
Recommended weight: 1. Made for Krea 2 Turbo (8 steps, CFG 1).
Prompt Examples
"ChucksRK, Photograph of a woman with light skin and brown hair in pigtails. She is topless, exposing her small to medium-sized breasts with visible nipples, and is wearing very short denim shorts and white knee-high socks with black stripes at the top."
"ChucksRK, Photograph of a woman with light brown skin, no visible hair, and no visible clothing on her upper body. She is kneeling on a wooden floor with her back to the camera, wearing black lace panties and black high-top sneakers with white soles and laces."
"ChucksRK, Photograph of a woman with light brown skin and long, wavy blonde hair. She is wearing a short, white, sleeveless dress that is lifted to reveal her black thong, exposing her buttocks."
Training
- Base model: Krea 2
- Type: Concept LoRA
- Steps: 4000
- Rank: 32
- Optimizer: adamw, constant learning rate
- Engine: ai-toolkit
Generation settings
Trained on Krea 2, and works on Krea 2 Turbo for faster generation.
- Raw: ~30 steps, guidance 3.5
- Turbo: ~8 steps, guidance 1.0
The gallery images were generated with krea2_turbo_mxfp8.safetensors, at 8 steps, guidance 1, LoRA weight 1.



















