OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image

可配置艺术风格与氛围的人物插画模板

Character Illustration Template with Configurable Art Style and Atmosphere

可复用的人物艺术插画模板：通过可配置的画风、成年人物、材质纹理、氛围、调色板与艺术运动生成统一而有触感的纵向肖像. A reusable image recipe made with gpt-image-2.5; explore the prompt and related works in the gallery.

可配置艺术风格与氛围的人物插画模板 — AI image creation
可配置艺术风格与氛围的人物插画模板

提示词 / Prompt

中文提示词

以用户上传的参考图作为主要可见人物的面部身份依据。在不与身份参考冲突的情况下，保留来源的场景、造型、服装、姿势、构图、光线和视觉风格。 创作一张4:5人物肖像插画，主体为a clearly adult woman quietly reading beside a sunlit window，采用hand-painted gouache illustration，并借鉴mid-century children's-book illustration的视觉语言。依据上传参考图保持这位明确成年人物的面部身份。画面呈现visible fine paper grain and layered matte brushwork，并以muted ochre, dusty rose, sage green and warm cream为主调。通过人物表情、姿势、留白和光线传达calm, reflective and gently whimsical的氛围。构成一个清晰亲密的场景，轮廓易辨、环境简洁，并将视觉焦点落在人物身上；保留所选媒材的笔触质感，不要把它磨平。色彩和谐、细节有所取舍，整体明确是插画而非照片。 不要额外人物、身份漂移、照片写实、3D渲染、光滑数码质感、杂乱、文字、标志或水印。输出一张完成度高的4:5图像。

English prompt

Use the uploaded reference image as the facial identity reference for the main visible person. Keep the source scene, styling, clothing, pose, composition, lighting and visual style unless they conflict with the identity reference. Create a 4:5 portrait illustration of a clearly adult woman quietly reading beside a sunlit window in hand-painted gouache illustration, informed by the visual language of mid-century children's-book illustration. Preserve the clearly adult subject's facial identity from the uploaded reference. Build the image with visible fine paper grain and layered matte brushwork and use muted ochre, dusty rose, sage green and warm cream as the dominant palette. Convey a calm, reflective and gently whimsical atmosphere through expression, gesture, spacing and light. Compose one clear, intimate scene with a readable silhouette, a simple supporting environment and a deliberate focal point on the person; let the chosen medium's marks remain visible rather than smoothing them away. Keep colors harmonious, details selective and the result recognizably an illustration, not a photograph. No extra people, identity drift, photorealism, 3D rendering, glossy digital finish, clutter, text, logos or watermark. Output one finished image at 4:5.

查看 API 模型

探索更多图片和视频提示词 · 生成图片 · 生成视频 · 在 AI 画布中创作