OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
成年人物照片的混乱搞怪低技术力涂鸦编辑
Chaotic Low-Tech Doodle Edits of Adult Portrait Photos
将输入的人物照片编辑为故意凌乱、幽默且低技术力的纸上涂鸦插画，保留成年人物的可识别身份，同时使用夸张比例、颤抖线条、蜡笔与马克笔纹理和手工速写本氛围。
提示词 / Prompt
中文提示词
将输入照片中的明确成年原创女性人物（人物身份使用参考 ref-10a-v1）编辑为一幅混乱、有趣且刻意低技术力的手工涂鸦插画。保留她的基本可识别特征和主要姿态，但将面部与身体处理为夸张、笨拙而不伤害性的卡通比例：略大的头部、不均匀的眼睛、歪斜的微笑、简化的小身体和故意不完美的解剖结构。使用粗糙的儿童速写线条、颤抖的手绘笔触、可见的涂改、重叠轮廓、偶然标记和不规则阴影，仿佛用便宜的马克笔、蜡笔或磨损的毛毡笔快速画在纸上。将背景改为简单而笨拙的卡通街景，包含歪斜建筑、树木、云朵和街道元素，透视不均匀但构图可读。上色故意粗心且不完全覆盖，保留蜡笔颗粒、马克笔晕染、纸张纹理和不一致的填色。加入划掉的线条、未完成细节、随机箭头、星星、漩涡和抽象涂鸦，但不要生成可读文字或真实个人信息。整体感觉幽默、自发、手工制作、充满活力、笨拙而温和，像儿童速写本与荒诞涂鸦艺术的混合；采用非对称构图、尴尬但有趣的取景和高纹理纸面。排除未成年人暗示、羞辱性文字、仇恨符号、真实logo、水印、可读文字、逼真照片质感、血腥、畸形恐怖和生成伪影。
English prompt
Edit the input photo of one clearly adult original woman, with her identity bound to character reference ref-10a-v1, into a chaotic funny handmade doodle illustration. Keep her basic recognizable features and main pose, but transform the face and body into exaggerated, clumsy, non-harmful cartoon proportions: a slightly oversized head, uneven eyes, a crooked smile, a simplified small body, and intentionally imperfect anatomy. Use rough childlike sketch lines, shaky hand-drawn strokes, visible corrections, overlapping outlines, accidental marks, and irregular shading, as if drawn quickly on paper with a cheap marker, crayon, or worn felt pen. Replace the background with a simple awkward cartoon street scene containing crooked buildings, trees, clouds, and street elements; keep the uneven perspective readable. Color carelessly and incompletely, preserving wax-crayon grain, marker bleed, paper texture, and inconsistent fill areas. Add crossed-out lines, unfinished details, random arrows, stars, swirls, and abstract scribbles, but do not create readable text or real personal information. The overall feeling is humorous, spontaneous, handmade, energetic, goofy, and gentle, like a child's sketchbook mixed with absurd doodle art. Use an asymmetrical composition, awkward but playful framing, and highly visible paper grain. Exclude implications of minors, humiliating text, hate symbols, real logos, watermarks, readable text, photorealistic finish, gore, frightening malformed anatomy, and generative artifacts.
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
- 黄昏
A quiet unposed fine art photograph of a young East Asian woman curled sideways in a wicker chair by the window at dusk, caught in a private unguarded moment, not posing. Long wavy dark brown hair falling loose over one shoulder and across her face, slightly tousled. Her gaze is lowered and averted
- 热血少年宝玉角色设定图
以当前固定参考肖像作为预览人物槽，为角色名“宝玉”制作少年漫风格的虚构示意设定图。面部与发型依据参考中可见特征；服装、姿势、配色和类型化光效均为可编辑的创作默认值，不代表对用户个人资料或性格的了解。 Create a fictional illustrative shonen-style character sheet named “宝玉,” using the current fixed portrait as the preview-subject slot. Base face and hair only on visible reference features; costume, p
- 黄昏藤椅
A quiet unposed fine art photograph of a young East Asian woman curled sideways in a wicker chair by the window at dusk, caught in a private unguarded moment, not posing. Long wavy dark brown hair falling loose over one shoulder and across her face, slightly tousled. Her gaze is lowered and averted
- 薰衣草墙花卉人像
无需外部参考，生成成年女性越过薰衣草色墙垂双臂持大花束的3:4写实时尚画面。
- 极简文字的个人色彩诊断图
以固定参考肖像为对象，通过服装色彩样片进行图表优先的视觉比较，文字简短，不写段落。结果是基于可见肖像的造型建议，不宣称经过校准的科学诊断。 Use the configured portrait as the subject and compare clothing-color swatches in a diagram-first layout. Keep labels brief and omit paragraphs. Present the result as a visual styling suggestion based on the visible portrait, not
- 古筝弹唱古典美人
一位成年表演者在明确标注为虚构演绎的直播间中扮演历史人物陈圆圆，弹奏古筝并演唱古风歌曲；固定参考仅用于表演者的面部身份，不代表陈圆圆的真实长相。弹幕保留原文“圆圆唱一曲”。 An adult performer portrays the historical Chen Yuanyuan in a clearly fictionalized livestream concept, playing the guzheng and singing a classical-style song. The fixed reference anchors only the performer’s face