OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
实体红色线绳节点关系映射系统海报
Entity Red String Node Relationship Mapping System Poster
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。 请将我上传的每一张照片分别制作成一张独立的高级设计海报，不多图拼接，每张照片单独输出。整体采用3:4竖版构图，上下两个区域高度严格1:1，各占画面50%。 上半部分保留原始照片，保持主体身份、结构、姿态、真实质感、自然光影和原有色彩氛围，仅进行轻微高级调色，使其具有艺术杂志、独立出版物与展览图像质感。为适配画幅，可自然扩展环境背景，但不得拉伸、扭曲或改变主体。 下半部分提取照片中最具识别性的**主体、轮廓、结构、姿态与叙事关系**，将其转译成一张真实可触摸的 **Physical String-based Systems Map / Tangible Node-link Visualization**。不要直接描绘原物，而是把主体拆解为少量具有意义的节点与关系：关键轮廓、结构转折、动作方向、空间位置或环境线索成为图钉式 Nodes，彼此之间使用真实线绳作为 Edges / Links，使原照片的视觉关系重新以实体网络显形，并仍能隐约辨认出原主体的身份与结构。 构图以一个明确的**核心节点或核心关系**作为视觉枢纽，其余节点围绕主体结构自然展开。线绳不是随机缠绕，而应根据原图的方向、比例、远近、连接与叙事逻辑建立关系；部分节点形成放射、聚合、三角、多边形与跨区域连接，使大量简单关系自然产生 **emergent geometry**。整体既复杂又有秩序，中心关系较密，外围逐渐疏松，保留充足负空间，避免把整个版面铺满。 材质必须具有真实实体装置感：使用细小图钉、针脚、棉线或细绳、纸质标签、手写痕迹和真实纸板表面，保留轻微线绳松紧差异、节点高度、交叉遮挡、针脚阴影与手工误差。整体像一件经过艺术指导的研究墙、系统设计实验或信息艺术装置，而不是电脑绘制的网络图，也不要出现赛博UI、数字发光线或廉价侦探板效果。 线绳以**鲜明但克制的朱红、珊瑚红或暖红色**作为主要关系色，在大量自然白、暖白、浅灰或与上方照片综合色温协调的极浅背景中形成视觉张力；图钉、纸签与少量标记可从上方照片提取局部特征色进行低面积呼应。整体颜色干净、现代、有生命力，避免暗褐、脏旧、血红恐怖感和过度复古做旧。 文字作为系统中的**Hand-lettered Annotation** 自由介入，不预设固定标题、地点、年份或菜单式信息。根据照片中的主体、动作、位置、情绪、关系或隐喻，自由生成少量关键词、短句、箭头、圈注或微型说明，并直接写在节点附近、线绳交汇处或留白区域。字体使用**细小、松弛、略带研究笔记感与书写偏差的手写注释字体**，让文字像观察过程中自然留下的思考痕迹，同时保持高级编辑设计的克制与可读性。 整体呈现**实体节点、红色线绳、关系映射、涌现几何、手写注释与大量留白**共同构成的高级实验视觉。无论主体是人物、动物、植物、建筑、器物、交通工具、自然景观或复杂场景，都应把“它是什么”进一步转译为“它的各部分如何发生关系”，形成具有研究感、艺术感、系统性与手工温度的实体信息可视化。避免随机红线、无意义节点、满版混乱、恐怖犯罪板、数字网络UI、卡通图钉、模板化思维导图和普通流程图。
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. Please turn each photo I upload into an independent high-end design poster, no multi-image stitching, each photo output individually. The overall composition uses a 3:4 vertical layout, with the top and bottom areas strictly 1:1 in height, each occupying 50% of the screen. The top half retains the original photo, maintaining the subject's identity, structure, posture, realistic texture, natural light and shadow, and original color atmosphere, with only slight high-end color grading to give it the texture of an art magazine, independent publication, or exhibition image. To adapt to the frame, the environmental background can be naturally extended, but the subject must not be stretched, distorted, or changed. The bottom half extracts the most recognizable subject, outline, structure, posture, and narrative relationship from the photo, translating it into a realistic and touchable Physical String-based Systems Map / Tangible Node-link Visualization. Do not directly depict the original object; instead, dismantle the subject into a small number of meaningful nodes and relationships: key outlines, structural transitions, movement directions, spatial positions, or environmental clues become pin-style Nodes, using real string as Edges / Links between each other, so that the visual relationships of the original photo are manifested again as a physical network, while the identity and structure of the original subject remain faintly recognizable. The composition uses a clear core node or core relationship as the visual hub, with other nodes naturally unfolding around the main structure. The strings are not randomly wound but should establish relationships based on the direction, proportion, distance, connection, and narrative logic of the original image; some nodes form radial, convergent, triangular, polygonal, and cross-regional connections, causing a large number of simple relationships to naturally produce emergent geometry. The whole is both complex and orderly, with denser central relationships and gradually sparser peripheries, retaining sufficient negative space to avoid filling the entire layout. Materials must have a sense of a real physical installation: use tiny pushpins, stitches, cotton thread or twine, paper labels, handwritten marks, and real cardboard surfaces, preserving slight differences in string tension, node height, cross-occlusion, stitch shadows, and manual errors. The whole looks like an art-directed research wall, system design experiment, or information art installation, rather than a computer-drawn network diagram, and should not have cyber UI, digital glowing lines, or cheap detective board effects. The string uses a vivid but restrained cinnabar red, coral red, or warm red as the primary relational color, creating visual tension against a large amount of natural white, warm white, light gray, or very light backgrounds coordinated with the comprehensive color temperature of the photo above; pushpins, paper tags, and a small number of marks can extract local characteristic colors from the photo above for low-area correspondence. The overall color is clean, modern, and vibrant, avoiding dark brown, dirty old, blood-red horror, and excessive retro distressing. Text intervenes freely as Hand-lettered Annotation in the system, without pre-setting fixed titles, locations, years, or menu-style information. Based on the subject, action, position, emotion, relationship, or metaphor in the photo, freely generate a small number of keywords, short phrases, arrows, circled notes, or miniature descriptions, and write them directly near nodes, string intersections, or white space areas. The font uses small, loose, handwritten annotation fonts with a slight sense of research notes and writing deviations, letting the text be like natural traces of thought left during the observation process, while maintaining the restraint and readability of high-end editorial design. Overall, it presents a high-end experimental visual composed of physical nodes, red strings, relationship mapping, emergent geometry, handwritten annotations, and a large amount of white space. Whether the subject is a person, animal, plant, building, object, vehicle, natural landscape, or complex scene, it should further translate 'what it is' into 'how its parts relate', forming a physical information visualization with a sense of research, art, systematicity, and manual warmth. Avoid random red lines, meaningless nodes, full-page chaos, horror crime boards, digital network UI, cartoon pushpins, templated mind maps, and ordinary flowcharts.
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
- 1
让材质更加干净整洁一些
- 漫步欧洲街头的三格时尚画报
垂直三格欧洲街拍时尚拼贴：以 ref-10a-v1 作为此可复用模板中女性主体的唯一面部身份参考；完整呈现街景、三种抓拍视角、服饰与配件、冰咖啡自拍及 Linkin Park 音乐播放器。面部特征按参考尽量保留，生成可能存在自然差异；64K 是高分辨率目标，不承诺实际像素尺寸。 | A vertical three-panel European street-style fashion collage using ref-10a-v1 as the sole facial identity reference for the female subject in this reusable te
- 俯拍夜幕下的便利店街头肖像
夜间街头时尚抓拍：从街对面较高楼层向下拍摄，一名年轻女子独自站在小型超市入口附近，略微偏离中心，呈现全身并保留开阔留白；穿白色 T 恤、水洗蓝色牛仔夹克、深色直筒牛仔裤和白色帆布运动鞋，单肩挂小手提袋。使用当前配置的固定面部参考 ref-10a-v1 作为本模板人物的面部参考。 | Candid night street-fashion scene viewed downward from an upper floor across the street: a young woman stands alone near a minimarket entrance, slightly off-c
- 最喜欢的角色进食动作
Add a food-specific eating action to the character in the configured reference image. Food is editable; defaults to a strawberry. The source mentions Nano Banana as its tool context. / 为配置参考图中的角色添加指定食物的进食动作；食物可编辑，默认一颗草莓。来源将 Nano Banana 作为工具语境提及。
- 橘红光影下的电影感极简人像
A photorealistic 4:5, 2K studio portrait with a fitted matte-black pique polo, serious upward off-camera gaze, low-angle face-and-shoulders framing, orange-red gradient, dramatic shadows and rim light. / 4:5、2K 逼真影棚人像：哑光黑色珠地棉 Polo 衫、严肃且略向上的镜头外视线、低角度面部与肩部构图、橙红渐变背景、戏剧性阴影与轮廓光。
- 红夹克女子四场景系列
以同一位黑色短发、带雀斑、穿红夹克的年轻女子为主角，分别呈现城市、海滩、山脉和夜街四个环境；每张单独成图，并使用同一固定身份参考保持人物一致。