OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
照片极简墨线小插画
Minimalist Ink Line Illustration of a Photo
来自 OpenNana 的图像提示词,已按本地图像分类和站点 gpt-image-2.5 归类整理。 使用时需上传人物参考图;本流程使用统一参考人物生成示例。

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。 将人物渲染为风格化插画,只保留参考图的面部身份特征;不要生成写实摄影人像。 仅根据上传的照片创建一件精美的“照片 + 简约水墨装饰画”艺术作品。 格式:纵向 3:4。 ### 顶部 —— 原始照片 使用大约上方 48–50% 的区域放置原始照片。 忠实且写实地保留照片。不要重绘、美化、替换、删除、复制或捏造重要元素。 保留: - 人物、动物、面部、服装、姿势和手势 - 食物和物品 - 建筑和环境 - 透视、光线、颜色和氛围 仅在必要时进行裁剪或等比例缩放。 ### 底部 —— 简约水墨装饰画 使用温暖的象牙色/自然的米白色纸张背景。 独立研究这张照片,并确定最能代表那一刻的一个主要视觉主体或一小群主体。 仅描绘重要的部分。移除大约 70–90% 不必要的背景细节。 识别度应主要源于: 轮廓 + 形状 + 颜色 + 姿势 + 1–3 个独特细节。 保持插图相对较小,留有大量的留白。 ### 风格 复古编辑风格 / 经典的印刷装饰画。 使用: - 纤细受控的深色墨水轮廓 - 略显不完美的轻微手绘轮廓 - 简单的几何形状 - 克制的平面色彩 - 微妙的色调变化 - 极简的纹理 - 柔和的落地阴影 - 清晰的形状分离 保持其迷人、图形化、整洁、怀旧且内敛。 使用比详细素描更少的笔触。 避免: 写实插画、水彩、绘画般的笔触、密集的素描、交叉排线、过多的轮廓、漫画风格、动漫/Q版、3D 渲染、完美的矢量几何或不必要的微小细节。 ### 标题 + 说明 在插图上方,创建: 一个简短的编辑标题:大约 2–4 个单词,灵感特别源自照片。 一个微型说明:大约 3–8 个单词,自然且内敛。 绝不使用通用标题,如 “Beautiful Moment”、“Sweet Memories” 或 “Wonderful Day”。 如果清晰可见可辨认的地点、地标、食物、品牌、事件或主体,可以使用其真实名称。绝不猜测。 ### 索引 根据主要主体在右下角添加一个微小的标签: - 食物/饮料 → PLATE NO. 01 - 动物 → PORTRAIT NO. 01 - 人物/群体 → MOMENT NO. 01 - 地点/建筑/景观 → VIEW NO. 01 - 物品/杂项 → STUDY NO. 01 对于人物 + 宠物,通常使用 MOMENT NO. 01。 ### 最终感觉 一个精美策展的个人视觉档案: 上方是真实照片 + 下方是简化记忆 + 简短的编辑标题 + 微型的人文说明 + 自适应索引 安静、极简、具收藏价值、优雅且一致。 重要提示:独立分析每一张上传的照片。绝不沿用之前图像中的主体、物体、地点、颜色、说明或细节。
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. Render the person as a stylized illustration that preserves the reference facial identity cues; do not turn the result into a photorealistic camera portrait. Create ONE refined PHOTO + MINIMAL INK VIGNETTE artwork based ONLY on the uploaded photograph. FORMAT: Vertical 3:4. ### TOP — ORIGINAL PHOTO Use approximately the upper 48–50% for the original photograph. Preserve the photo faithfully and photorealistically. Do not redraw, beautify, replace, remove, duplicate, or invent important elements. Preserve: - people, animals, faces, clothing, poses and gestures - food and objects - buildings and environment - perspective, lighting, colors and atmosphere Only crop or scale proportionally when necessary. ### BOTTOM — MINIMAL INK VIGNETTE Use a warm ivory / natural off-white paper background. Study THIS photograph independently and identify the ONE main visual subject or small group that best represents the moment. Illustrate only what matters. Remove roughly 70–90% of unnecessary background detail. Recognition should come mainly from: silhouette + shape + color + pose + 1–3 distinctive details. Keep the illustration relatively small with generous negative space. ### STYLE Vintage editorial / classic printed vignette. Use: - thin controlled dark-ink outlines - slightly imperfect hand-drawn contours - simple geometric forms - restrained flat colors - subtle tonal variation - minimal texture - soft grounding shadow - clean shape separation Keep it charming, graphic, tidy, nostalgic and understated. Use fewer strokes than a detailed sketch. Avoid: photorealistic illustration, watercolor, painterly brushwork, dense sketching, cross-hatching, excessive outlines, comic-book style, anime/chibi, 3D rendering, vector-perfect geometry, or unnecessary tiny details. ### TITLE + CAPTION Above the illustration, create: ONE short editorial title: approximately 2–4 words, inspired specifically by the photograph. ONE micro-caption: approximately 3–8 words, natural and understated. Never use generic titles such as “Beautiful Moment,” “Sweet Memories,” or “Wonderful Day.” If a recognizable place, landmark, food, brand, event, or subject is clearly visible, its real name may be used. Never guess. ### INDEX Add a tiny bottom-right label based on the main subject: - Food/drink → PLATE NO. 01 - Animal → PORTRAIT NO. 01 - Person/group → MOMENT NO. 01 - Place/architecture/landscape → VIEW NO. 01 - Object/miscellaneous → STUDY NO. 01 For a person + pet, normally use MOMENT NO. 01. ### FINAL FEEL A beautifully curated personal visual archive: REAL PHOTOGRAPH ABOVE + SIMPLIFIED MEMORY BELOW + SHORT EDITORIAL TITLE + TINY HUMAN CAPTION + ADAPTIVE INDEX Quiet, minimal, collectible, elegant, and consistent. IMPORTANT: Analyze every uploaded photograph independently. Never carry over subjects, objects, locations, colors, captions, or details from previous images.
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
相关作品
- Z世代少女与拉布布的橙调时尚大片
以当前配置的人像作为泛化人物身份参考,创作橙色影棚中的超写实时尚大片:人物、真人大小的毛绒Labubu玩偶与英国短毛猫共同入镜。 | Use the currently configured portrait as the generic subject identity reference for a hyper-realistic orange-studio fashion editorial featuring the subject, a life-sized furry Labubu character, and a British Shorthair cat.
- 情人节玫瑰巧克力报纸大片
使用当前面部与肩部参考保持人物身份;人物仰卧于可读报纸上,搭配红西装、玫瑰、巧克力与心形光影,呈现俯拍情人节杂志大片。 | A top-down Valentine’s Day editorial using the current face-and-shoulders reference for likeness, with readable newspapers, a red blazer, roses, chocolates and heart-shaped light.
- 你在看什么
昏暗日式和室内,一名有韩国偶像感的年轻女生背对镜头跪坐在榻榻米上,高机位俯拍,镜头从斜上方俯视她的背部与回望的面孔。她上身微微前倾,肩背向中间收拢,脊柱沟在裸露的背部形成柔和凹陷,肩胛骨轮廓微微凸起;腰线骤然收窄,与丰满的臀部形成极致腰臀比,跪坐姿态使臀部压向小腿与脚跟,布料紧贴身体勾勒出圆润的臀部曲线。她回头越过右肩直视镜头,下巴靠近肩头,颈部拉出细长线条,黑长直齐刘海整齐覆在额前,日式公主切发型两侧鬓发笔直垂落至脸颊,发尾贴住下颌与颈侧,其余长发顺背部垂落,几缕发丝搭在裸露的肩胛与绑带之间。 她身穿黑色紧身露背连体衣,后背大面积裸露,从肩胛下缘一直开到后腰,高叉剪裁,没有裙摆,布料紧紧包
- 九十年代复古胶片淡紫连帽衫人像
以当前配置的 ref-10a-v1 作为本次泛用人脸身份参考;保留年轻女性面容、浅柔肤色、蓬松黑色长发、淡紫旧感连帽衫、90年代一次性相机快照、拍立得与胶带照片背景、柔和闪光和怀旧色调。示例图仅作出处,不是额外身份材料。 | Use configured ref-10a-v1 as the generic face-identity reference for this run; preserve the young woman’s face, soft pale complexion, loose long black hair, worn pastel-lavender hoodie, 9
- 超写实护照证件照六宫格
使用当前配置的人像参考作为本次“我”的面部身份及可见服装输入,创作适用于官方证件或护照的专业影棚头肩照;一张竖版打印纸上均匀排布六张相同的3×2证件照。 | Use the configured portrait reference as this run’s face-identity and visible-outfit input for “me”; create a professional studio head-and-shoulders image suitable for official ID or passport use, with six identical ID ph
- 你的专属梦幻水彩情人节贺卡
将当前配置的人像作为本次实际上传图像,把照片中的单人转绘为风趣、可爱、独一无二的情人节贺卡主体;采用创意、风格化、梦幻的水彩表现,不要求保留原照片像素或原背景。 | Use the currently configured portrait as this run’s actual uploaded image and restyle its person as the central subject of a witty, cute, one-of-a-kind Valentine’s Day card in a creative, stylized, dreamy watercolor t