Premium character LoRAs
Original synthetic characters, bundles and AI tools are in my shop:
Join the community on Discord: https://discord.gg/nB79wRNtMT
Pegging
A concept LoRA for Krea 2 focused on pegging: a woman wearing a strap-on harness and dildo with a man, in doggy style, missionary, standing or riding positions. It gives an amateur photo look.
Usage
Start with the trigger word PeggingRK, then describe the strap-on (harness, dildo color and size), the position and who is where, how their bodies touch, their bodies, hair and expressions, what they wear or that they are nude, the camera angle and the room, and end with the light.
PeggingRK, Photograph of a <body> woman with <hair> wearing a <color> strap-on harness, <position> with a <body> man, <angle> in a <room>. The lighting is <light>.
Recommended weight: 1. Made for Krea 2 Turbo (8 steps, CFG 1).
Prompt Examples
"PeggingRK, Photograph of a woman with light skin and black, shoulder-length hair with one side shaved. She is wearing a black leather harness with straps, a black leather collar, and black leather garters. A black leather bag with sex toys, including a dildo and a vibrator, is on the couch to her left."
"PeggingRK, Photograph of a woman with light skin and dark hair in a ponytail, wearing black strappy lingerie with a harness and black stockings, and an adult man with light skin, nude, on a bed with white and colorful patterned sheets. The woman is standing and wearing a strap-on harness with a black dildo, penetrating the man from behind in a doggy style position."
"PeggingRK, Photograph of a nude woman with light skin and dark body hair. A man's hand, with a light skin tone, holds a realistic, flesh-toned dildo with a black strap-on harness. The dildo is inserted into her anus."
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.