<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>Flashing and Flaunting</h2>A concept LoRA for Krea 2 focused on women flashing and showing off: lifting their top or dress, pulling a bra or bikini aside, pulling down shorts or panties, indoors and outdoors. It gives an amateur photo look.<h3>Usage</h3>Start with the trigger word <code>FlashFlauntRK</code>, then describe the woman (skin, hair, body), what she reveals and how (lifting, pulling aside, pulling down), what she wears, her expression and pose, the camera angle and the place, and end with the light. Saying exactly how she flashes brings out the effect the most.<code>FlashFlauntRK, Photograph of a woman with &lt;skin&gt; and &lt;hair&gt;, lifting her &lt;top / dress&gt; to reveal her &lt;breasts / ...&gt;. She wears &lt;...&gt;, &lt;pose&gt; &lt;place&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>"FlashFlauntRK, Photograph of a topless woman with fair skin and dark hair, partially covered by a green jacket that she is lifting to expose her breasts. She wears unbuttoned blue jeans that are slightly pulled down to reveal the top of her black underwear."</blockquote><blockquote>"FlashFlauntRK, Photograph of a topless woman with light skin and long blonde hair. Her gray, off-the-shoulder top is pulled down to expose her breasts."</blockquote><blockquote>"FlashFlauntRK, Photograph of a woman with medium brown skin and long, straight dark brown hair. She is topless, exposing her medium-sized breasts with visible nipples. She wears a black leather jacket that is unzipped and pulled open, and high-waisted camouflage leggings with a black belt that has white text."</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: 724dda5791f3c1df4ae378484925ac333825473aa4731eb3778a18cd05bd727d