<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>Anal</h2>A concept LoRA for Krea 2 focused on anal sex: couples in doggy style, spooning, cowgirl and close-ups, nude or partly dressed, in bedrooms and on sofas. It gives an amateur photo look.<h3>Usage</h3>Start with the trigger word <code>AnalRK</code>, then describe the people (skin, hair, bodies), the position and the penetration in plain words, what they wear or that they are nude, the camera angle and the place, and end with the light. Naming the position and the angle brings out the effect the most.<code>AnalRK, Photograph of a man and a woman having anal sex in &lt;position&gt;. &lt;bodies and details&gt;. The camera is &lt;angle&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>"AnalRK, Photograph of a woman with light skin and dark hair. A man's penis is partially inserted into her anus. The camera angle is close-up and from behind."</blockquote><blockquote>"AnalRK, Photograph of a woman with light skin and brown hair, styled in loose waves. She is on all fours on a white bed, with a man with light skin and a tattoo on his right arm, who is fully nude, standing behind her and penetrating her anus. Another man with dark skin is kneeling in front of her, penetrating her vagina."</blockquote><blockquote>"AnalRK, Photograph of a nude woman with light tan skin and dark hair in a ponytail, positioned on all fours on a bed with gray sheets. Her buttocks are prominently displayed, and she is being penetrated anally by a man with a circumcised, erect penis. The camera angle is from behind the woman."</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: 0cea9af84279de73eff3111228969b5b27be9bf4d2961af4e65f649404ceb2e4