Anime Girl in Rotating Whip-Pan City Transition Sequence

A 15-second image-to-video prompt that composites a 2D anime girl into live-action city streets, using rotating whip-pan transitions to move between seven locations with matching outfit changes. The camera and environment rotate while the character stays stable and grounded, with beat-synced cuts and directional motion blur.

This clip could not be loaded — it may have been removed from X.
田中勇道 | AI画像・動画生成 @yudotanaka ·
View on X ↗

Prompt

MiniMax H3で回転トランジション動画。Seedanceだと何度やっても、動画のような回転ができませんでした。プロンプトはどのキャラクターにも対応してます。
Prompt:
## REFERENCE
Use Reference Image 1 as the identity reference for the girl. Preserve her identity throughout.
She is a clean 2D anime-illustrated character composited into a cinematic live-action city environment.
## CORE CONCEPT
15-second sequence built from rotating whip-pan transitions between cinematic city street locations.
Every transition: the top of the frame swings right, the bottom swings left, with directional motion blur. The outgoing street exits this way; the next street enters the same way and settles level.
The girl stays anime-style, stable, grounded — only the camera/environment rotates.
Each location carries a different outfit suited to its setting, time of day, and mood. Clothing changes happen only between locations, never through visible morphing.
## LOCATION & OUTFIT PROGRESSION
1. Original outfit — neon-lit downtown crossing at night, wet asphalt reflections
2. Elegant black dress — upscale glass-tower/hotel street at night, warm lighting
3. Red stage costume — live-house/club street, colorful signage, blurred crowd
4. White blouse, dark skirt — daytime business district, glass office buildings
5. Casual modern outfit — sunny shopping/residential street, convenience store front
6. Dark purple fantasy outfit — dusk alley with izakaya lanterns and vending machines
7. Return to the original outfit — back to the original neon crossing
Maintain the same identity and outfit-appropriate look across all seven locations.
## TIMELINE
0.0–2.0s: centered at the neon crossing. Slow push-in. Whip-pan begins at the end.
2.0–3.5s: crossing exits via whip-pan; hotel street enters, settles level, revealing the black dress. Brief push-in.
3.5–5.0s: black dress/hotel street, medium shot closing in. On the beat, whip-pan reveals the club street/red stage costume.
5.0–6.5s: club street, upper-body framing, short zoom. Fast whip-pan reveals the business street/white blouse-dark skirt.
6.5–8.0s: business street, full-body, subtle hair/clothing movement. Whip-pan reveals the shopping street/casual outfit.
8.0–9.5s: shopping street, slow push-in to upper body. Fast whip-pan reveals the izakaya alley/dark purple outfit.
9.5–11.0s: izakaya alley, medium → upper-body framing, short zoom and lateral movement. Strong whip-pan with motion blur reveals another clearly different street/outfit.
11.0–12.5s: new location/outfit. Whip-pan settles level; girl stays stable in frame.
12.5–14.0s: three rapid location+outfit changes on beat, same whip-pan each time. Full body → upper body → chest-up. Each transition reveals a clearly different street/outfit.
14.0–15.0s: return to the original neon crossing, centered. Gentle whip-pan into level alignment. Slow push-in. End on a clean centered frame.
## ROTATING WHIP TRANSITION
Every transition: top of frame swings right, bottom swings left, with directional motion blur, simultaneous with translation. Roughly 10–30° of apparent rotation per transition. Smooth momentum, controlled easing. Reads as a camera whip-pan/spin cut through real locations — not an illustrated panel sliding.
## CRITICAL ROTATION RULE
Rotation always moves the same way: top of frame tilts right, bottom tilts left. Never reverse mid-sequence. Never make the girl herself spin — only the camera/environment rotates. Her body, head, arms, and legs stay stable and grounded in each shot.
## CAMERA / EFFECTS
Push-in/pull-back, rotating whip-pan, directional motion blur, slight scale changes, brief impact shake, beat-synced hard cuts, short freeze moments. Keep effects clean and controlled.
## VISUAL STYLE
style_separation:
  character: clean 2D cel-shaded anime illustration, faithful to Reference Image 1, non-sexualized design
  environment: cinematic live-action city street style — accurate architecture, signage, blurred/anonymous pedestrians, realistic lighting/reflections/materials
retained_elements: the girl's anime style never shifts toward realism; the streets never shift toward illustration.
Visual variety comes from location, lighting, outfit, and framing while identity and rendering style stay identical.
## CHARACTER CONSISTENCY
Preserve identity from Reference Image 1. Only outfit, pose, framing, location, and lighting may change. No additional characters or duplicates. Background pedestrians stay anonymous/blurred and never resemble the girl.
## RESTRICTIONS
Girl stays upright and grounded — body never spins. Clothing changes only between locations — no morphing. Anatomy stays correct — no extra limbs or uncontrolled transformations. No readable text, logos, watermarks, or commercial branding. Camera shake stays brief and controlled — no excessive shake or random unmotivated scene changes.
Priority: stable character identity, coherent cinematic city environments, clear outfit changes matched to each location, smooth whip-pan transitions with consistent direction, precise beat synchronization.
@pixverse #pixversecpp
? How to use this prompt ▾
  1. Copy the prompt using the green "Copy prompt" button above.
  2. Open your model — launch Seedance 2.0 on its official interface.
  3. Paste & generate — keep the verbatim prompt text for best adherence. Set aspect ratio to 9:16 and clip duration to 15s.

What makes this prompt work

Every insight below is verified against benchmark generation parameters, not asserted. How our prompt engineering benchmarks work →

CAMERA
"zoom" is a core cinematic camera technique for establishing spatial immersion and subject framing. Also present: "pan", "tilt", "push-in".
LIGHTING
"neon, warm tone, cinematic lighting" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD
"energetic, cinematic" — Mood and aesthetic tone are explicitly directed to maintain emotional consistency throughout the scene.
DURATION
At 15s, this clip is optimized for high temporal coherence and fluid, realistic motion physics.
MODEL
Seedance 2.0 (ByteDance) provides the underlying diffusion and motion architecture. Camera, lighting and duration cues transfer across models — what differs is how literally each model interprets motion.
PROMPT LANGUAGE
The prompt is written in Chinese. This library keeps every prompt in its original language rather than translating it — the exact words are what was conditioned during generation.
Seedance 2.5 BytePlus Cloud Partner

Tell bigger stories with Seedance 2.5

Create AI videos up to 30 seconds long with richer image, video, and audio references. Ideal for complex ideas that need consistency and control.

Explore on BytePlus Official ByteDance Enterprise Cloud