GPT Image 2AI 提示词
Social Media Video Feed Screenshot — Sora 2 Prompt
Create realistic Chinese social media app video feed mockups with customizable UI elements, user profiles, and stunning background scenes for design projects.
提示词 · EN
type
social media video app interface screenshotmain_visual
subject
young Asian woman, long dark hair blowing in wind, white top, looking over shoulder at camerasetting
{argument name="background location" default="Guangzhou Canton Tower by the river at sunset"}lighting
golden hour, warm sunset glowui_layout
top_status_bar
elements
4labels
item 1
9:41item 2
signalitem 3
wifiitem 4
100 batterytop_navigation
elements
6labels
item 1
menu iconitem 2
经验item 3
团购item 4
关注item 5
{argument name="active tab" default="推荐"}item 6
search iconright_interaction_bar
elements
6labels
item 1
profile photo with red plusitem 2
heart icon with {argument name="like count" default="23.6万"}item 3
comment icon with 1.6万item 4
star icon with 2.8万item 5
share icon with 3.7万item 6
spinning music recordbottom_left_text
elements
3labels
item 1
{argument name="username" default="@小鹿的日常"}item 2
{argument name="caption" default="吹着晚风，看着日落，这一刻好治愈~ 🌅"}item 3
music note icon with 原声 @小鹿的日常创作的原声bottom_navigation
elements
5labels
item 1
首页item 2
朋友 with red badge 2item 3
square plus buttonitem 4
消息 with red badge 5item 5
我关于这个提示词
Create realistic Chinese social media app video feed mockups with customizable UI elements, user profiles, and stunning background scenes for design projects. 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 visual、ui layout 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。
如何使用这个提示词
- Copy the full prompt JSON into your preferred AI image generator.
- Select a model that excels at UI mockups and photorealistic details (e.g., Sora 2, DALL-E 3, or Midjourney).
- Customize the
{argument}variables—such asbackground location,username,caption, andlike count—to match your creative vision. - Generate the image and review the output for UI accuracy and realism.
- Re-generate or tweak specific variables if you need adjustments to layout or style.
