<h1 id="premium-character-loras">Premium character LoRAs</h1>Original synthetic characters, bundles and AI tools are in my shop:<a target="_blank" rel="ugc" href="https://rkrra.com/civitai">https://rkrra.com/civitai</a>Join the community on Discord: <a target="_blank" rel="ugc" href="https://discord.gg/nB79wRNtMT">https://discord.gg/nB79wRNtMT</a><h2>Public Flashing</h2>A concept LoRA for Krea 2 focused on women flashing in public places: lifting a top or dress, pulling down pants or opening a coat in streets, parks, beaches, stores, parking lots and cars. It gives an amateur photo look.<h3>Usage</h3>Start with the trigger word <code>PublicFlashingRK</code>, then describe exactly what she reveals and how, what she wears, the public place in detail and whether other people are around, her body, skin and hair, her expression and the camera angle, and end with the light. The more precise the place, the stronger the effect.<code>PublicFlashingRK, Photograph of a woman with &lt;hair&gt; in &lt;outfit&gt;, &lt;lifting her top / opening her coat&gt; to flash her &lt;...&gt; in &lt;public place&gt;, &lt;people around / empty&gt;. The lighting is &lt;light&gt;.</code>Recommended weight: 1. Made for Krea 2 Turbo (8 steps, CFG 1).<h3>Prompt Examples</h3><blockquote>"PublicFlashingRK, Photograph of a woman with light olive skin and long, straight, dark brown hair with bangs. She is topless, lifting a black sweatshirt to expose her breasts, and is wearing tight, black, high-waisted leggings and white sneakers. She is standing in a brightly lit store aisle with shelves of folded clothes in the background."</blockquote><blockquote>"PublicFlashingRK, Photograph of a woman with light skin and blonde hair in two braids. She is sitting on a pink towel on a sandy beach, smiling at the camera."</blockquote><blockquote>"PublicFlashingRK, Photograph of a fair-skinned woman with long blonde hair and a slim build. She is standing in a snowy parking lot, smiling at the camera."</blockquote><h3>Training</h3><ul><li>Base model: Krea 2</li><li>Type: Concept LoRA</li><li>Steps: 4000</li><li>Rank: 32</li><li>Optimizer: adamw, constant learning rate</li><li>Engine: ai-toolkit</li></ul><h3>Generation settings</h3>Trained on Krea 2, and works on Krea 2 Turbo for faster generation.<ul><li>Raw: ~30 steps, guidance 3.5</li><li>Turbo: ~8 steps, guidance 1.0</li></ul>The gallery images were generated with <code>krea2_turbo_mxfp8.safetensors</code>, at 8 steps, guidance 1, LoRA weight 1.

Files with SHA256: 86a015851b53265a1432ab197fe981811518a981942bb8583cc202c591ee0707