<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>Amateur</h2>A concept LoRA for Krea 2 focused on amateur home photos: mirror selfies, phone shots, lingerie, topless and nude, in real bedrooms and bathrooms with everyday light and clutter.<h3>Usage</h3>Start with the trigger word <code>AmateurRK</code>, then describe the woman (skin, hair), what she wears or that she is topless or nude, the framing (mirror selfie, phone held up, casual snapshot), the room, and end with the light. Naming the selfie or snapshot framing brings out the effect the most.<code>AmateurRK, Photograph of a woman with &lt;skin&gt; and &lt;hair&gt;, wearing &lt;...&gt;. She is taking a &lt;mirror selfie / snapshot&gt; in &lt;room&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>"AmateurRK, Photograph of a woman with light skin and wavy blonde hair, wearing a sheer pink lingerie set with floral embroidery. She is standing in front of a mirror, taking a selfie with her right hand, holding a black smartphone. The photo is an amateur mirror selfie with slight blur."</blockquote><blockquote>"AmateurRK, Photograph of a nude woman with light skin and blonde hair, partially visible. The photo has an amateur phone-camera look, with a slight blur. The angle is slightly above her waist, focusing on her torso and upper thighs."</blockquote><blockquote>"AmateurRK, Photograph of a woman with light skin and long blonde hair, lying topless on a bed. The photo has a slight blur and noise, typical of an amateur phone photo taken in a bedroom setting."</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: 921b37b35d003636d3d14f950200ba27581adbc7f610435084fb86f5f7e011b4