GoodCase.aiGoodCase.aiAI Case Evidence Library
RankingsCasesSkillsCreatorsFavoritesSubmitDaily
中文EN
Agent Access →
GoodCase.ai · AI Case Evidence LibraryLoading the case library.
ChangelogFeedback
GoodCase.aiGoodCase.aiAI Case Evidence Library
RankingsCasesSkillsCreatorsFavoritesSubmitDaily
中文EN
Agent Access →
AI VideoX (Twitter)2026-08-08Evidence L1#x#seedance-2.5#capcut#paid-partnership#thread-continuation#prompt-truncatedSeedance 2.5

Seedance 2.5 涩谷街头K-pop舞蹈同步字幕

Sharon Riley avatarCreatorSharon Riley →

Seedance 2.5 生成的涩谷街头K-pop快闪翻跳视频,四名舞者依次变换菱形、横排、V字三种队形完成舞蹈段落。画面叠加与舞点精确同步的复古大字字幕,逐句随节拍淡入淡出。

View original source ↗

Prompt

30-SECOND K-POP PUBLIC DANCE COVER — SHIBUYA, TOKYO (with synced typography)
Generate a 30-second horizontal 4:3 realistic live-action K-pop girl group public dance cover video, using the provided first frame as the exact visual starting point, with retro bold-typography captions appearing in sync with the choreography, styled like halftone poster-text overlays (bold condensed display font, high-contrast color against the scene, subtle grain texture matching the background).
TYPOGRAPHY STYLE
Font: bold condensed display, poster-style
Placement: upper third or side margin, never covering faces or hands
Animation: quick fade/slide-in synced to the beat, holds for its duration, clean fade-out before the next line
Color: high-contrast against Tokyo evening tones (cream/gold/white lettering with soft drop shadow)
One line active on screen at a time
SCENE & LOCATION
Shibuya street, Tokyo, Japan, natural evening light, authentic public dance-cover environment — kanji/hiragana/katakana shop signs, convenience stores, cafés, boutiques, vending machines, parked bicycles, overhead wires, glass reflections, soft neon beginning to glow, blurred distant pedestrians. No recognizable logos or brand signage.
FRAME & CAMERA
Horizontal 4:3, fixed frontal camera, eye-level, ~5 meters distance, full-body framing, stable documentary style. Subtle push-in only during RINA's highlight, then returns to full frame. No cuts, rotation, extreme zooms, or handheld shake.
CHARACTERS — EXACTLY 4 DANCERS
RINA (center): long straight black hair, babypink cropped racing jacket, ivory crop top, charcoal cargo shorts, brown ankle boots
YERI (left): light brown high ponytail, light blue cropped knit jacket, beige camisole, faded black wide-leg jeans, cream sneakers
SOO (right): silver-grey hair, navy off-shoulder top, rose-gold waist chain, charcoal pleated skirt, black platform shoes
MINA (back): dark reddish-brown curly hair, olive bomber jacket, grey crop tee, navy straight-leg pants, off-white platform sneakers
No fifth dancer, no duplicates, no overlapping bodies, no identity swaps.
TIMELINE WITH SYNCED TYPOGRAPHY
0–6s — OPENING DIAMOND
RINA center-front, YERI front-left, SOO front-right, MINA back-center. Hand opening, side steps, shoulder rhythms, crossed-arm accents, face-framing gestures, hip accents.
Caption: "SAME STREET, NEW BEAT" — fades in at 1s, holds to 5s, fades out.
6–10s — RINA HIGHLIGHT
RINA: chest pop, head tilt, direct eye contact, finger point to camera. Others restrained, framing her. Subtle push-in then return.
Caption: "ALL EYES, ONE GIRL"* — appears exactly as RINA points at camera (6.5s), holds through push-in, fades by 9.5s.
10–14s — DIAMOND → HORIZONTAL LINE
Smooth half-step transitions, MINA steps out from behind RINA into full visibility. Wrist flicks, arm sweeps, hip accents, toe taps once stabilized.
Caption: "SHIFT THE SHAPE" — slides in as formation begins moving (10s), fades out once line stabilizes (13.5s).
14–19s — HORIZONTAL LINE CHORUS
Heel-toe shuffles, knee bounces, chest pops, shoulder rhythms, toe taps. SOO performs controlled body-wave highlight on the right.
Caption: "WAVE IT OUT" — appears as SOO's body-wave begins (15s), fades before formation shifts (18.5s).
19–23s — RETURN TO DIAMOND + RIPPLE
Diamond reforms, MINA repositions opposite RINA, fully visible. YERI initiates ripple body wave: YERI → RINA → SOO → MINA.
Caption: "RIPPLE THROUGH" — timed to appear exactly as the ripple starts at YERI (20s), fades as it reaches MINA (22.5s).
23–27s — FINAL CHORUS
Upward arm points, hip accents, shoulder rhythms, toe taps, chest pops, rising energy, natural hair/clothing movement.
Caption: "TURN IT UP" — appears on the first upward arm point (23.5s), fades before final transition (26.5s).
27–30s — FINAL V FORMATION + FREEZE
RINA front-middle, YERI back-left, SOO back-right, MINA mid-back-right. Coordinated freeze pose, symmetrical arm lines, feet planted, completely still for the final second.
Caption: "FREEZE FRAME" — slides in as the freeze locks (28s), holds steady and crisp through the final loop-ready frame (30s) — no fade-out, ends on screen.
VISUAL STYLE
Realistic live-action street photography — genuine skin texture, individual hair strands, realistic clothing materials, accurate body proportions, natural shadows, evening illumination, storefront reflections, documentary cinematic composition. Typography sits as a poster-style overlay layer, not baked into the environment — legible, clean, and non-intrusive to the dancers.
STRICT NEGATIVE REQUIREMENTS
No anime, cartoon, 3D/CGI look, stage lights, studio set, extra dancers, duplicated people, overlapping bodies, distorted anatomy/hands/feet, teleportation, sudden formation changes, rapid camera movement, camera rotation, extreme zoom, watermarks, subtitles unrelated to the timed captions, or recognizable copyrighted logos/signage. Captions must stay legible and never obscure faces or hands.
FINAL OUTPUT
30 seconds, horizontal 4:3, realistic live-action K-pop public dance cover, Shibuya street, Tokyo, exactly 4 consistent dancers, full-body frontal camera, three formations, synchronized choreography with six timed typography captions matching each beat, stable camera, natural evening lighting, c

Reusable method

Key decisions

Check whether camera continuity, transition logic, and action resolution all hold in the final result.

Adapt it to your subject

Extract “target result → the subject, scene, camera movement, and final action → constraints” as a reusable template for similar work.

Where it breaks

Run single-variable comparisons around shot length, transitions, and motion amplitude. Record the model, cost, and failures; turn it into a Skill only after it repeats reliably.

Recommended models

Seedance 2.5
Stability
Cost
Medium
This case has not yet been distilled into a Skill.Request it in feedback →
Sharon Riley avatar

Creator

Sharon Riley

Sharon Riley focuses on AI video production and publishes across X and X (Twitter). “Two-Idol K-pop MV, Shot by Shot” is the current representative case, built with Seedance 2.5 with its stability retest open to votes.

Editor’s pickAI VideoHigh source heat
View creator →

Keep exploring

Explore related cases.

View all AI Video Case →
AI VideoX08/07/2026MAX →

16mm Analog Morning Vlog

A highly detailed video prompt for Seedance 2.5 mimicking a handheld 16mm analog morning vlog of a woman walking her dog, focusing on realistic imperfections and film texture.

Skill · POV and vlog presence

Prompt

CAMERA: Handheld DV 16mm daily vlog footage. The video MUST begin with her holding the camera at arm's length in selfie mode while stepping outside her apartment building with her

Source heat
81
Stability
View case →
AI VideoX08/06/2026TechHalla →

90s Diner Time Freeze Effect

A cinematic video prompt for Seedance 2.5 featuring a high-physics diner collision where time freezes, allowing a character to interact with suspended objects before resuming in real-time.

Prompt

Photorealistic cinematic 1990s American diner, red vinyl booths, neon signs, chrome details, checkerboard floor, soft natural window light mixed with warm practicals, subtle handhe

Source heat
83
Stability
View case →
AI VideoX08/04/2026John →

Bamboo Toy Car Transformation Vlog

An incredibly detailed action prompt for a 30-second handheld POV video featuring a girl with a bamboo toy that triggers a car transforming into a giant robot.

Skill · POV and vlog presence

Prompt

纯属虚构的荒诞动作短片。100%真实手机实拍质感,iPhone纪录片风格,30秒手持一镜到底,无剪辑、无转场。自然日光,轻微呼吸式镜头运动,偶发自动对焦迟疑,轻微滚动快门,真实动态模糊,镜头边缘带少量指纹和灰尘。所有变形、机械运动、撞击和碎片效果都必须具有沉重的现实物理反馈,呈现为全尺寸机械装置与实景特效,绝不能出现电子游戏、动画或廉价CG质感。保留现场原始

Source heat
67
Stability
View case →
GoodCase.ai · AI Case Evidence LibraryEach detail page keeps the work, method, creator, and retest evidence in one reading path.
ChangelogFeedback