Premium character LoRAs
Original synthetic characters, bundles and AI tools are in my shop:
Join the community on Discord: https://discord.gg/nB79wRNtMT
Why Even Wear Anything
A concept LoRA for Krea 2 focused on outfits that barely cover anything: sheer and see-through fabrics, mesh, fishnet, micro bikinis, tiny strings, cut-outs and extreme slits, worn out and about or at home. It gives an amateur photo look.
Usage
Start with the trigger word BarelyWearRK, then describe the outfit precisely (sheer, mesh, fishnet, micro bikini, strings, cut-outs), its colour and what shows through or is exposed, her body, her pose, the camera angle and the place, and end with the light. Naming how little the outfit covers brings out the effect the most.
BarelyWearRK, Photograph of a woman with <hair> wearing a <sheer / mesh / micro> <dress / bikini / top> that barely covers <...>, <pose>, <angle> in a <place>. The lighting is <light>.
Recommended weight: 1. Made for Krea 2 Turbo (8 steps, CFG 1).
Prompt Examples
"BarelyWearRK, Photograph of a woman with a medium skin tone and long, wavy black hair. She is wearing a sheer, metallic, silver dress that is extremely revealing, showing her nipples, breasts, and pubic area through the mesh fabric."
"BarelyWearRK, Photograph of an adult woman with fair skin and long, wavy blonde hair. She wears a sheer, white, halter-neck dress with extreme slits that expose her breasts, nipples, and buttocks."
"BarelyWearRK, Photograph of a woman with fair skin and long, wavy brown hair. She is wearing a black, open-front coat over a sheer, brown mesh top that reveals her large breasts with visible nipples."
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.



















