OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
压角构图文化展览海报设计
Corner Composition Cultural Exhibition Poster Design
以压角构图把边缘文字与图形压力引向中心主体的可复用文化展览海报模板，支持主题、标题、颜色和机构信息替换。
提示词 / Prompt
中文提示词
制作一张 9:16 竖幅、具有成熟文化展览与编辑平面设计气质的压角构图海报。主题为“Lotus Lantern Gathering（传统莲花灯展）”，中文主标题为“莲灯映古城”，英文标题为“Lotus Lantern Gathering”，中心主体为“a complete lotus-lantern installation（完整的莲花灯装置）”。采用“dual-corner diagonal pressure”的边缘压迫方式，角部使用“large Chinese characters and archival information panels”；只使用一套与主题真实相关的辅助纹样“subtle lotus-petal archival linework”，主色调为“warm ivory, vermilion, and charcoal”，强调色为“jade green”，日期/机构信息为“2026 / CITY CULTURE ARCHIVE”。 核心不是简单把文字放进四角，而是利用边缘的大型中文字体、色块、信息区或图案向内施加视觉压力，自然“夹”出中心主体。中心主体保持完整、稳定并承担约 40%-60% 的视觉重量，不为配合构图故意倾斜或变形。四角压迫时要有主次，1-2 个角承担主要重量；对角压迫时两个对角为主、另外两角只放小信息；三角围压时保留一个轻角；单角重压时由对角小元素回应。大型中文标题可局部裁边、贴边或与主体轻微叠压，但必须清晰可读。英文标题、日期、机构和主题说明集中在 2-3 个区域，以超大中文、中号英文和极小信息形成清晰层级。背景不可完全空白，可加入极淡的主题纹样、档案信息、结构图、材料纹理或说明残影，但不抢主体。信息密度中高而不杂乱：第一眼读主体与压角关系，第二眼读中文标题，第三眼读英文、日期和辅助信息。即使移除小字，画面仍应是一张成立的文化展览海报。
English prompt
Create a 9:16 vertical cultural-exhibition poster with a mature editorial graphic-design temperament. Set the theme to “Lotus Lantern Gathering” (a traditional lotus-lantern exhibition), the Chinese main title to “莲灯映古城”, the English title to “Lotus Lantern Gathering”, and the central subject to “a complete lotus-lantern installation” (a complete lotus-lantern installation). Use “dual-corner diagonal pressure” as the edge-pressure method; place “large Chinese characters and archival information panels” in the corners; use one auxiliary pattern genuinely related to the theme, “subtle lotus-petal archival linework”; set the main palette to “warm ivory, vermilion, and charcoal”, accent color to “jade green”, and date/organization line to “2026 / CITY CULTURE ARCHIVE”. The idea is not merely to put text in four corners: large Chinese typography, color blocks, information panels, or patterns at the edges should apply inward visual pressure and naturally squeeze out the central subject. Keep the central subject complete, stable, and responsible for about 40%-60% of the visual weight; never tilt or deform it to fit the layout. For four-corner pressure, establish hierarchy with 1-2 dominant corners; for diagonal pressure, make two diagonal corners primary and keep the other two informational; for a three-corner wrap, deliberately release one corner; for single-corner heavy pressure, let a smaller diagonal element respond. Large Chinese type may crop at an edge or lightly overlap the subject, but must remain clearly legible. Concentrate the English title, date, organization, and theme description in 2-3 areas, creating hierarchy through extra-large Chinese type, medium English type, and tiny information. The background must not be completely blank: add only very faint theme patterns, archival information, structural diagrams, material textures, or explanatory traces, never competing with the subject. Keep information density medium-high but ordered: first read subject and corner pressure, second the Chinese title, third the English, date, and supporting information. The poster must remain a valid visual work even if small text is removed.
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
- 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。
- 吃西瓜的古怪年轻女性手绘编辑插画
一位古怪的年轻成年女性在厨房桌旁吃西瓜，呈现半写实、松散有质感的传统手绘编辑插画；保留指定的发型、服装、姿势、神情、色彩和素描本质感。