Back 中文 CC Prompt Galaxy

Confident woman on urban street AI Image Prompt

Prompt

Modern urban commercial street, with a shop selling paper as the background storefront. The protagonist is a 30-year-old woman, wearing a navy blue blazer + white shirt + black straight-leg trousers + black leather shoes. She has big wavy hair, weighs 100 jin (about 110 lbs), and has a confident and approachable smile. She walks from the storefront toward the middle of the street facing the camera, spreading her arms and making guiding gestures with a brisk pace. The scene includes a variety of store signs, pedestrians and traffic, street greenery and seating, creating a vibrant urban streetscape. The sunlight is bright with natural soft shadows. Composition centers on the person, with plenty of breathing space. The camera follows her movement with slight handheld shake, transitioning naturally from medium shot to close-up to extreme close-up. Each frame overlays dynamic subtitles: 0:00 "什么叫靠谱" (yellow-black bold), 0:01 "去年在 今年在", 0:02 "年年都在", 0:03 "淡季在", 0:04 "旺季在", 0:05 "四季常在", 0:06 "不诋毁同行", 0:07 "不内卷", 0:08 "用品质和服务", 0:09 "一路前行", 0:10 "这才是", 0:11 "靠谱" (two large characters filling the screen center, with a strong rhythmic sound effect). At the end, she stands in a prominent spot on the street, arms open, looking directly at the camera with a firm tone. The voiceover subtitles sync: "什么叫靠谱?去年在,今年在,年年都在;淡季在,旺季也在,四季常在。不诋毁同行,不内卷,用品质和服务,一路前行——这才是靠谱." Style is professional and approachable, with a brisk rhythm. 4K HD quality, moderate color saturation.

AI Image Content Analysis

Content: Subject (30-year-old woman, navy blazer, etc.) + Scene (urban commercial street, paper shop storefront) + Action (walking briskly to street, spreading arms) + Camera (medium shot to close-up, handheld shake) + Subtitle and voiceover timeline (0-11 sec) + Style (professional approachable, 4K HD, moderate color saturation)

Pros: Rich details: explicit subtitle timeline and full voiceover for precise control; strong rhythm: progressive action and subtitles create dynamic feel.

Cons: Overly long prompt: subtitles and voiceover largely redundant, increasing AI comprehension load; challenging for AI: simultaneous multi-frame subtitles and voiceover, handheld shake may be difficult to fully reproduce.

Reference image: No obvious reference-image dependency

Author
用户572580
Type
Video
Aspect ratio
9:16
Size
720 × 1280
Added
2026-06-09

Source materials are collected from publicly accessible web pages. Contact us if a rights issue needs review. Copyright & Privacy