Which AI model works best for this prompt?

This prompt is optimized for Sora 2, but it also works well with other text-to-image models such as Midjourney, DALL·E 3, or Stable Diffusion.

Can I change the UI elements or the scenic background?

Absolutely. The prompt uses variables (arguments) that you can modify. Replace default values for scenery, subject appearance, or UI text like username and captions.

What kind of output will I get?

You'll get a realistic screenshot of a mobile short-video app interface, complete with a scenic travel video, navigation bars, action buttons, and overlays as described.

GPT Image 2AI 提示词

Travel Short Video App UI Screenshot — Sora 2 Prompt

Generate a realistic mobile short-video app screenshot featuring a scenic travel video with mountain lake and standard social media UI overlay.

提示词 · EN

type

移动端短视频 App 界面截图

main_content

scene

{argument name="scenic background" default="绿松石色的高山湖泊、翠绿的松树林、崎岖的雪山、蓝天白云"}

subject

{argument name="main subject" default="留着长黑发、反戴黑色棒球帽并穿着白衬衫的女性，倚靠在木栅栏上欣赏风景"}

ui_elements

status_bar

time

14:53

icons

item 1

信号栏

item 2

Wi-Fi

item 3

电池 78%

top_navigation

left_icon

汉堡菜单

tabs

item 1

直播

item 2

同城

item 3

关注

item 4

关于这个提示词

Generate a realistic mobile short-video app screenshot featuring a scenic travel video with mountain lake and standard social media UI overlay. 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。

这条提示词使用结构化 JSON 组织信息，包含 type、main content、ui elements 等字段。保留这种层级能让模型更清楚地区分画面主题、布局、界面元素和细节约束。

使用时建议先小幅修改主体、场景、镜头和色调，再生成多个版本对比构图与细节。这样页面内容对用户有实际帮助，也避免把模型名或标签机械堆在正文里。