<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>Latinas</h2>A concept LoRA for Krea 2 focused on Latina women: tan, olive and brown skin, curves, lingerie, bikinis, tight dresses and jeans, topless and nude, mirror selfies and posed shots. It gives an amateur photo look.<h3>Usage</h3>Start with the trigger word <code>LatinasRK</code>, then describe the woman (skin tone, hair, makeup), her curves, what she wears or that she is topless or nude, her pose and the place, and end with the light. Describing her skin tone and curves brings out the effect the most.<code>LatinasRK, Photograph of a Latina woman with &lt;tan / olive / brown&gt; skin and &lt;hair&gt;, &lt;wearing ... / nude&gt;. She is &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>"LatinasRK, Photograph of a woman with medium brown skin and long black hair in a mirror selfie. She has a curvy body type with large breasts and a visible belly button."</blockquote><blockquote>"LatinasRK, Photograph of a tan-skinned woman with long, straight, black hair and a slim, curvy physique."</blockquote><blockquote>"LatinasRK, Photograph of a woman with medium brown skin and long, straight black hair. She has a curvy body with large breasts, which are exposed in a pink bikini top that has a deep V-neck."</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: 91bb998f058d7bea0869f169c65a8511f90ff1f5435db8794ffa509da1760578