<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>Funsized</h2>A concept LoRA for Krea 2 focused on petite, short women: small, slim frames, shown in mirror selfies and full-body shots at home, dressed, in lingerie, topless or nude. It gives an amateur photo look.<h3>Usage</h3>Start with the trigger word <code>FunsizedRK</code>, then describe her small, slim frame and short stature, anything that shows her size (furniture, a doorway, a taller person), her body, skin and hair, what she wears or that she is nude, her pose and framing and the room, and end with the light. The more precise the framing, the stronger the effect.<code>FunsizedRK, Photograph of a petite, short woman with &lt;hair&gt;, wearing &lt;... / nude&gt;, &lt;pose&gt; in &lt;room&gt;, &lt;mirror selfie / full-body shot&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>"FunsizedRK, Photograph of a woman with light skin and brown hair in a loose, straight style. She is topless, exposing her small, flat chest with small, pink nipples. The woman has a slim, petite frame and is lying down, taking a selfie from an overhead angle."</blockquote><blockquote>"FunsizedRK, Photograph of a woman with light skin and straight, medium-length, light brown hair with bangs. She has a slim, petite frame and is standing in a doorway, taking a mirror selfie. She is topless, exposing her small, perky breasts with pink nipples, and is wearing pink, low-rise panties."</blockquote><blockquote>"FunsizedRK, Photograph of a woman with light skin and long, straight blonde hair. She has a slim, petite frame and is topless, exposing her small, round breasts with light pink areolas and nipples."</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: 452ef3668e8a8f2c5cb0652f0a24796bff2aad82a7ea4f6924689b13a36c4b0a