This LoRA was trained on a set of 87 curated images of the artist <a target="_blank" rel="ugc" href="https://danbooru.donmai.us/posts?tags=yuming_li">Yuming Li</a>, with both booru-style tags and natural language.A style LoRA for soft, painterly fantasy illustrations with expressive brushwork, deep shadows, and luminous color. The training set includes portraits, fantasy characters, angels, animals, and a few wider scenes. Many images use violet and blue shadows with warm highlights, but the style can also work with brighter colors when prompted.MOSS Image Version:Base model: MOSS Image BaseStarting strength: 0.8, ranging from 0.6-1.0 works fine depending on what u want for style.Anima Version:Base model: Anima Base v1.0Trigger: <code>@yumingli</code>Starting LoRA strength: 0.6 I would recommend you to start with 0.6, you can bump it up to like 1.0 with the right conditions (quality tags).For a stronger style effect, I trained it with additional style tags, try adding:<code>painterly, soft brushwork, dramatic lighting,</code>Example prompt: <code>masterpiece, best quality, score_9, score_8, score_7, year 2025, newest, highres, absurdres, very aesthetic,</code><code>@yumingli, painterly, soft brushwork, dramatic lighting,</code><code>1girl, dark-skinned female, long purple hair, sitting beside a window, blue dress, warm lamplight</code>

Files with SHA256: 531433699c39a60f974fa52a2ff8dc0da8495e669817537cd6df9828de1dd760