A LoRA that creates anime-rendered subjects in a photorealistic world (this version only makes the subject's face/hair cel-shaded, while their body/limbs/clothes remain real). This is my first LoRA, so feedback is welcome :)Trigger: <code>ANIRL, anime-rendered face and hair</code>Strength: Start at 1.0, increase if the subject's face is too realisticExample Prompt:<pre><code>ANIRL, anime-rendered face and hair, a young woman with a blonde bob in a gray sweater sits at a kitchen table, slowly stirring a mug of coffee. Morning light comes through the window behind her. She looks down at the mug, then glances toward the window. Static camera, medium shot, natural lighting</code></pre>Notes/Tips:<ul><li>Designed and tested for T2VA; no clue about I2VA</li><li>Keep face/hair descriptions simple otherwise the model will push toward realism</li><li>For multiple subjects, tag each one separately (e.g. <code>an anime-rendered young woman</code>, <code>a fully photorealistic man</code>)</li><li>If faces are distorted, try a closer camera position. It doesn't do well with distant subjects</li><li>I trained on mostly young adults, so older/mature subjects might require higher strength</li></ul>Based on the awesome ANIRL Krea 2 style by @llikswonskcalb: <a target="_blank" rel="ugc" href="https://civarchive.com/models/2762978/bss-styles-for-krea2?modelVersionId=3113108">https://civarchive.com/models/2762978/bss-styles-for-krea2?modelVersionId=3113108</a>

Files with SHA256: 96960d49dc3c8bc171b148f49829882c4c1e9a026d885964d5538073ce56e610