主题:图像中的人物

创作一张 3:4 的超写实抓拍夜间活动照片,呈现未经编辑的 iPhone 后置摄像头闪光灯效果。照片以胸部到面部的高度手持拍摄,靠近主体,具有广角感(约 2426 毫米等效焦距),边缘略有畸变,景深较深,使主体、附近人群和赛道背景清晰可辨。

垂直中近景构图,从腰部到略高于头部。主体站在赛车场栏杆附近,身体略微侧向一边,一只手臂随意地弯曲在栏杆旁,另一只手臂放松。构图感觉仓促而本能——略微偏离中心,背景元素重叠并部分裁剪。

直射的机载闪光灯正面打光,强烈照亮主体,在皮肤、头发和赛车夹克上形成刺眼的强光,肩膀后方阴影骤然消失。体育场灯光、LED 屏幕和标牌在背景中呈现为过曝的强光和柔和的焦外光斑。在较暗的人群和结构区域,低水平的噪点和颗粒感依然可见。

手机风格的曝光优先考虑主体,提升高光并压缩阴影。头发丝、夹克接缝、印刷标志和面部轮廓上出现轻微的计算锐化。

主体的表情警觉而略显分心,嘴唇微微张开,目光偏离画面,仿佛正在对附近的现场活动做出反应。这一刻感觉像是活动进行中,未经摆拍。

主体穿着一件黑白相间的赛车风格夹克,上面有明显的赛车运动品牌标识和补丁,内搭一件修身内衣,展现出有结构感的面料、微妙的光泽和自然的褶皱。一条细项链在锁骨处捕捉到微小的闪光灯高光,腰部可见牛仔裤和皮带。

环境是一个拥挤的夜间赛车场,有栏杆、观众、赞助商标牌、LED 屏幕、灯光设备和结构梁。背景感觉繁忙、嘈杂、充满活力,增加了视觉上的杂乱和动感。

图像应给人一种在现场赛车活动中用 iPhone 闪光灯拍摄的自发照片的感觉——混乱、充满活力和人性化。没有电影般的灯光,没有编辑摆拍,没有美颜修饰。

请勿改变主体的面部特征或比例。主体必须与参考图像 1000% 相同。
YouTube 缩略图 - 超真实抓拍夜间赛车照片,搭配 iPhone 闪光灯美学
0
0
0

一个高度详细的提示,用于生成一张超现实、混乱且充满活力的夜间照片,模拟未经编辑的 iPhone 后置摄像头闪光灯美学。它指定了赛车场上的一个主体,刺眼的正面闪光灯照明营造出突然的阴影衰减,广角畸变,以及可见的噪点/颗粒,旨在呈现出与参考图像相同的自发、不做作的外观。

Language
EnglishDeutschEspañolFrançais日本語한국어Português中文
Created24 days ago
Last updated24 days ago
Creator

Services with a clipboard icon will copy the prompt to your clipboard first.

Version History
Prompt documentation
Comments (0)
Please log in to leave a comment.

Be the first to comment

to start the conversation.

Related Prompts
EnglishDeutschEspañolFrançais日本語한국어Português中文

A JSON array prompt designed to generate four separate images of celebrities (Addison Rae, Ana de Armas, Sydney Sweeney) in winter sportswear, but placed in snowy mountain or gym settings. Each entry specifies the celebrity, outfit, location, and key background elements (fox, deer, wolf, Matterhorn) to create themed, vertical images.

0
0
0

EnglishDeutschEspañolFrançais日本語한국어Português中文

A detailed system prompt for Nano Banana Pro to generate high-click-through-rate horror-themed YouTube thumbnails. The AI acts as a horror concept artist, focusing on creating a cyber-horror aesthetic, emphasizing the uncanny gap between the 'Nano Banana' name and its 'super-performance AI' nature. It includes specific instructions for composition, lighting, and integrating a reference character as a terrified witness.

0
0
0

EnglishDeutschEspañolFrançais日本語한국어Português中文

A sophisticated system prompt designed for Nano Banana Pro to create high Click-Through Rate (CTR) thumbnails based on principles of cognitive science (neuroscience, psychology, behavioral economics). It instructs the AI to adopt the persona of an expert art director, analyze input text, and follow a detailed thinking process (Thinking Mode) before drawing, focusing on facial activation, pop-out effects, and minimizing cognitive load. It includes specific design and typography instructions.

0
0
0

EnglishDeutschEspañolFrançais日本語한국어Português中文

A highly structured JSON prompt for generating an ultra-photorealistic portrait of a woman seated outdoors, holding a fluffy Pomeranian dog, emphasizing casual elegance, soft flash illumination, and the aesthetic of an Instagram night portrait captured with an iPhone.

0
1
0

EnglishDeutschEspañolFrançais日本語한국어Português中文

A highly specific JSON prompt for generating an ultra-photorealistic, candid outdoor portrait of a young woman at a race event, focusing on detailed subject definition, specific pose (shielding eyes from sun), and strict negative constraints against text overlays.

0
0
0

EnglishDeutschEspañolFrançais日本語한국어Português中文

A detailed prompt for Nano Banana 2 to transform a subject from a reference image into a cute 3D anime chibi character. The prompt emphasizes preserving the subject's likeness, race, and skin tone while applying classic chibi proportions, rendering it as a high-quality, glossy 3D model with vibrant colors and a premium collectible aesthetic.

0
0
0