Premium character LoRAs
Original synthetic characters, bundles and AI tools are in my shop:
Join the community on Discord: https://discord.gg/nB79wRNtMT
Huge Dildos
A concept LoRA for Krea 2 focused on women with very large dildos: oversized toys of every shape, color and material, held, ridden or used, with suction cups and bases. It gives an amateur photo look.
Usage
Start with the trigger word HugeDildosRK, then describe the dildo precisely (size relative to her body, shape, color, material, base), how she holds, rides or uses it, her body, skin and hair, her pose and framing and the place, and end with the light. The more precise the dildo, the stronger the effect.
HugeDildosRK, Photograph of a woman with <body> and <hair>, <holding / riding> a huge <color> <material> dildo <how>. She is <pose / framing> <place>. The lighting is <light>.
Recommended weight: 1. Made for Krea 2 Turbo (8 steps, CFG 1).
Prompt Examples
"HugeDildosRK, Photograph of a woman with light skin and long blonde hair, styled in loose waves. She is holding a large, black, silicone dildo with a suction cup base, which is partially inserted into her vagina."
"HugeDildosRK, Photograph of a fair-skinned woman with bright pink, shoulder-length bob haircut. She holds a large, realistic-looking, flesh-toned dildo in her right hand, which is significantly larger than her hand and has a visible base."
"HugeDildosRK, Photograph of a woman with light skin and brown hair, wearing a sheer black mesh bodysuit that exposes her breasts and nipples. She is sitting on a bed with white sheets, legs spread apart, holding a large, dark brown, realistic-looking dildo with her right foot. Her toes are wrapped around the base of the dildo, which is positioned between her legs."
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.