<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>Rear View Close-Up</h2>A concept LoRA for Krea 2 focused on explicit rear-view close-ups: buttocks, anus and vulva seen from behind, bent over, on all fours or lying face down, with hands spreading the buttocks or panties pulled aside. It gives an amateur, candid photo look, close framing and natural home settings.<h3>Usage</h3>Start with the trigger word <code>GodAssholeRK</code>, then describe the woman (skin and hair), the pose and camera angle, what she wears or pulls aside, and what is visible between the buttocks.<code>GodAssholeRK, Photograph of a woman with &lt;skin&gt; and &lt;hair&gt;. She is &lt;bent over / on her hands and knees / lying face down&gt;, viewed from behind. She is wearing &lt;stockings / a thong pulled aside / nothing&gt;. Her buttocks &lt;are spread by her hands&gt;, showing &lt;anus and vulva&gt;.</code>Recommended weight: 1. Made for Krea 2 Turbo (8 steps, CFG 1).<h3>Prompt Examples</h3><blockquote>"GodAssholeRK, Photograph of a woman with fair skin and dark hair, wearing black lace stockings and a black garter belt. Her buttocks and anus are prominently displayed, with her right hand pulling her buttocks apart to reveal her vulva."</blockquote><blockquote>"GodAssholeRK, Photograph of a woman with light skin. She is positioned on her hands and knees, viewed from behind. Her buttocks are prominently displayed in the center of the frame. She is wearing a red top that is pulled up and a white thong pulled to the side."</blockquote><blockquote>"GodAssholeRK, Photograph of a woman with dark brown skin, bent over, the camera close behind her, her vulva and anus exposed."</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: 9657ce77f6217bb20d38925f4f0af0bc7bd1996c0aeed46bfc300e40fb0c81bd