PromptweetPromptweet
Thư viện / Cinematic realistic / Korean Woman's Casual Afternoon in Seoul

Korean Woman's Casual Afternoon in Seoul

Cinematic realisticVlogSeedance 2.5

A young Korean woman spends an ordinary afternoon walking through modern Seoul, visiting a café, and enjoying a riverside path, shot in natural handheld smartphone footage.

Prompt727 lượt copy
Create a 30-second photorealistic live-action video of a clearly adult Korean woman in her early 20s spending an ordinary afternoon in modern Seoul. SUBJECT: Young Korean woman with natural facial features, realistic skin texture, minimal makeup, black wavy hair with wispy bangs. She wears a dark navy fitted knit top, relaxed beige wide-leg trousers, white sneakers, and a small black shoulder bag. Keep her face, hairstyle, clothing, body proportions and accessories completely consistent from beginning to end. CAMERA: Modern high-end smartphone footage recorded casually by a friend. Vertical handheld video, natural walking movement, slight hand shake, realistic smartphone autofocus, subtle exposure adjustment, authentic motion blur and realistic HDR. No cinematic camera moves, no slow motion, no artificial film effects. STORY — ONE CONTINUOUS AFTERNOON: 00:00–00:05 The video begins with the woman walking out of a Seoul subway station into bright daylight. She looks at her phone while walking, then notices the camera and gives a quick natural smile. The camera follows behind and slightly to her side. 00:05–00:10 She walks across a real Seoul intersection while the pedestrian signal is green. Cars and buses move naturally in the background. She waits briefly at the opposite curb, adjusts her shoulder bag and looks toward her friend. 00:10–00:15 She enters a small modern café. The camera follows her through the glass door. She approaches the counter, orders an iced drink, pays with her smartphone, receives the drink and immediately takes a sip. 00:15–00:20 She leaves the café and continues walking along a modern Seoul street. She laughs at something her friend says off-camera. While walking, she briefly fixes her bangs with one hand and keeps the drink in her other hand. 00:20–00:25 She reaches a riverside pedestrian path. The city skyline and river are visible behind her. She stops beside the railing, places her drink down, and looks across the water while wind naturally moves her hair. 00:25–00:30 She suddenly looks toward the skyline and points at something in the distance. She turns toward the camera and says naturally, "Look at that." The camera follows her pointing gesture and ends on the real sunset skyline over the river. VISUAL REALISM: Make this look like genuine footage recorded by a real person, not an AI video or commercial. Natural imperfect human movement, realistic walking physics, believable background pedestrians, accurate reflections, realistic shadows, natural hair and clothing movement, physically correct object interaction and consistent anatomy. Absolutely no extra fingers, duplicated hands, malformed hands, warped faces, duplicated people, floating objects, disappearing objects, changing clothes, changing hairstyle, facial identity drift, unnatural body movement, impossible reflections or physically impossible interactions. The woman must always have anatomically correct hands with five fingers. Phones, cups, bags and all other objects must maintain their shape and position logically between shots. AUDIO: Natural location sound only: footsteps, city traffic, subway ambience, café sounds, wind, distant conversations and her brief natural dialogue. No music. PRIORITY: Generate a FULL MOVING VIDEO with visible continuous actions throughout all 30 seconds. Every segment must contain meaningful physical movement. Do not create a still image, slideshow, audio-only output, or static portrait.
Có khoá nhất quán: một đặc điểm mà prompt yêu cầu model giữ nguyên.
Cách dùng prompt này
  1. 1
    Copy prompt

    Dùng nút copy phía trên để lấy đúng văn bản như đã viết.

  2. 2
    Dán vào Seedance 2.5

    Dán nguyên văn vì camera, ánh sáng và thời lượng đã được nêu rõ sẵn.

  3. 3
    Đổi chủ thể, giữ nguyên cấu trúc

    Chỉ đổi chủ thể hoặc bối cảnh để có kết quả dễ đoán nhất; cách diễn đạt tương tự cũng dùng được cho model khác.

Tỉ lệ khung hình
9:16
Góc quay
handheld · tracking · close-up · wide shot · over-the-shoulder
Ánh sáng
natural light · golden hour · cinematic · realistic HDR
Không khí
relaxed · authentic · everyday
Thời lượng
30s
Độ khó
Advanced
Model
Seedance 2.5
Bao gồm
Khoá chủ thể

Thêm từ Seedance 2.5

Điều gì làm prompt này hiệu quả

Mỗi nhận định dưới đây được đo trên 376 prompt của thư viện này, không phải khẳng định suông.

Góc quay

‘handheld’ được dùng trong 174 prompt của thư viện, xếp hạng #4 trong các thuật ngữ camera xuất hiện ở đây.

Ánh sáng

‘natural light’ xuất hiện trong 164 prompt trên toàn thư viện, xếp hạng #1.

Tỉ lệ khung hình

9:16 được dùng trong 69/376 prompt của thư viện. Việc nêu rõ tỉ lệ quan trọng hơn là chọn tỉ lệ nào.

Tính nhất quán

Prompt này có khai báo khoá nhất quán, giúp giữ chủ thể dễ nhận ra xuyên suốt clip.

Model

Seedance 2.5 chiếm 71.8% thư viện (270/376 prompt).

Độ khó

Đánh dấu advanced, dựa trên số lượng thông số (camera, ánh sáng, thời lượng, khoá) được kết hợp cùng lúc.