What is the best AI model for this prompt?

This prompt is designed for Sora but works well with most advanced text-to-image models like Runway Gen-3 or Kling that support cinematic, photorealistic outputs.

Can I change the subject's clothing or background?

Absolutely. The prompt uses variables like `{hat type}` for easy customization. You can also edit the descriptive text to change other elements like the hoodie color or background style.

What style of output can I expect?

Expect a hyper-realistic, editorial photograph with a cinematic mood, strong subject focus from the 85mm lens, and a beautifully blurred, colorful graffiti wall background.

GPT Image 2AI Prompt

Urban Street Portrait with Graffiti — Sora 2 Prompt

Create a cinematic, shallow depth-of-field street portrait with a confident model, vibrant bokeh background, and warm, natural lighting.

PROMPT · EN

电影感城市街头人像，一位时尚年轻女性随意坐着，戴着 arghat type: 芥末黄针织帽、圆框眼镜，身穿黑色廓形连帽衫和蓝色破洞牛仔裤，柔和自然光，浅景深，背景为色彩鲜艳且虚化（焦外成像效果）的涂鸦墙，居中构图，直视镜头，表情冷静自信，面部细节丰富，自然皮肤纹理，暖色调柔和调色，街头服饰美学，编辑摄影风格，85mm 镜头，超写实，4K

About this prompt

Create a cinematic, shallow depth-of-field street portrait with a confident model, vibrant bokeh background, and warm, natural lighting. Use it as a Concept Art starting point for GPT Image 2: keep the visual structure and style constraints intact, then swap in your own subject, brand, or scene.

Start by replacing hat type, then keep the camera, composition, and material cues in the same order. This makes the output easier to compare across variations.