OpenZhenZhen AI 提示词画廊 · gpt-image-2.5 · image
薄荷绿与淡紫灰档案记录封面风格
Mint Green and Lavender Gray Archive Record Cover Style
以用户上传的人物参考图绑定档案人像主体，制作4:5全出血现场记录封面。固定淡紫灰底与薄荷绿文字系统，并提供学科、字标、记录堆栈、符号和手持物件变量。
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，保留来源的构图、服装、姿势、光线和视觉风格。 制作一张4:5纵向、全出血的“现场记录封面”海报。背景是单一去饱和灰紫色 #6E6672，可表现为纯色摄影棚墙面或黄昏天空；无纹理、无渐变条纹。全图唯一饱和色为春意薄荷绿 #7FE68D，其他颜色仅来自自然皮肤和布料。服装使用不会与薄荷绿竞争的静谧蓝、橄榄绿、铁锈红、木炭黑或银色。 人物采用胸部以上取景，略微偏离中心，三分之四侧脸或近侧面，眼睛向上并远离镜头。人物在脸部附近拿起 a ribbon microphone 并认真研究它，可以是阅读、倾听或检查，但绝不向相机展示。使用凉爽环境填充光与侧面硬暖主光，保留皮肤自然光泽、汗水和毛孔，皮肤上有镜面高光，绝不磨皮调平；背景最多出现一个柔和失焦的线索。 顶部放置字标“RESONANCE”：极细长的超粗无衬线全大写薄荷绿字，横跨全宽并被两侧边缘裁切；人物头部必须遮挡其中2–3个字母，使字标从不完全清晰，但仍可辨认。左侧中部堆叠3–4行薄荷绿窄体大写记录文字“TAPE 031 ROOM TONE 18 20 ARCHIVE B”，每行一项，行距宽松，无标语和标点。堆栈下方放置一个小薄荷绿符号“four-point star”。底部添加4–6行极小薄荷绿大写记录信息，包含地点、记录者、格式、日期和备注。所有文本都应像索引、时间、坐标或格式记录，不要写营销口号。 整体以 field recording 为学科语境，手持物件在不加说明的情况下暗示该学科。文字标识被遮挡是签名式特征；坚持一个背景数值和一种强调色，不添加第二种饱和色。采用轻微剪贴感、网印颗粒和真实档案封面触感，不要高端抛光、复杂场景、额外装饰、logo、水印或其他品牌。
English prompt
Use the uploaded reference image as the facial identity reference for the main visible person. Keep the source composition, clothing, pose, lighting and visual style unless they conflict with the identity reference. Create a 4:5 vertical, full-bleed field-record cover poster. Use one desaturated gray-mauve value #6E6672 across the background, appearing as a plain studio wall or dusk sky with no texture and no gradient banding. The only saturated color anywhere is spring mint #7FE68D; all other colors come only from natural skin and cloth. Wardrobe may use muted navy, olive, rust, charcoal or silver, but nothing that competes with the mint. Frame the adult subject chest-up, slightly off-center, in three-quarter or near-profile view with the eyes lifted away from the lens. The subject holds a ribbon microphone near the face and studies it by reading, listening or inspecting; never present it to camera. Use cool ambient fill with a hard warm side key, retaining natural skin gloss, sweat and pores with specular highlights; never flatten the skin with retouching. Allow at most one soft out-of-focus background clue. Place the wordmark “RESONANCE” at the top: ultra-condensed heavy sans-serif capitals in mint, spanning the full width and cropped by both frame edges. The head must always eclipse 2–3 letters, so the wordmark is never fully legible while remaining orthographically recognizable. Stack 3–4 lines of mint condensed capitals “TAPE 031 ROOM TONE 18 20 ARCHIVE B” at mid-height on the left, one record item per line with generous leading, no slogans and no punctuation. Place one small mint glyph “four-point star” beneath the stack. Add 4–6 lines of tiny mint capitals at the bottom containing location, recordist, format, date and notes. Every text string must read like an index, time, coordinate or format record, never marketing copy. Use field recording as the discipline context; the held object should name the discipline without a caption. Treat occlusion of the wordmark as the signature. Keep one background value and one accent color, with no second saturated color. Add slight collage feel, screen-print grain and authentic archive-cover tactility. Do not add high-end polish, complex scenes, extra decoration, logos, watermarks or other brands.
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
- 吃我一脚
Photorealistic professional e-commerce photography, extreme low-angle frontal perspective directly facing the model's barefoot raised foot, the large sole and pointed toes fill the foreground with strong foreshortening, dramatic near-to-far perspective and visual pressure, elegant young woman with l
- 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。