What AI models work best with this prompt?

This prompt is optimized for Sora 2 but also works well with Midjourney, DALL·E, and Stable Diffusion for realistic candid photography.

Can I customize the subject and style?

Absolutely! Replace the `subject` argument with any person description (e.g., 'a student reading a book') and the `style` argument with any photography style (e.g., 'vintage film') to get varied results.

What quality can I expect from the generated images?

You'll get high-resolution, photorealistic candid shots with natural lighting and genuine expressions, perfect for storytelling or concept art.

Realistic Subway Candid Prompt — Photorealistic AI Images | sora2hub

GPT Image 2AI 提示词

Realistic Subway Candid Prompt — Sora 2 AI Photo

Generate lifelike subway candid shots with this simple yet powerful AI prompt. Customize subject and style for endless realistic portraits.

提示词 · EN

argsubject: 一位在地铁上低头看手机的美丽女性; argstyle: 抓拍照片。

关于这个提示词

Generate lifelike subway candid shots with this simple yet powerful AI prompt. Customize subject and style for endless realistic portraits. 它更适合作为 GPT Image 2 的概念艺术起点：先保留画面结构、主体关系和风格约束，再替换成你的品牌、人物或场景。

使用时优先替换 subject、style 等占位符，并保持镜头、构图和材质描述的顺序不变。这样更容易获得稳定的画面结果，也方便继续做多版本对比。

如何使用这个提示词

Copy the prompt from above.
Choose your AI model (Sora 2, Midjourney, DALL·E) and paste the prompt.
Tweak the subject and style variables (e.g., change "beautiful woman" to "elderly man" or "candid photo" to "cinematic shot").
Generate your image and adjust settings as needed.