Anime Rooftop Chase to Game Splash Screen

An anime-style game cinematic that follows a ponytailed girl sprinting across a rooftop and leaping between buildings with a wolf, ending on a looping idle splash screen. It uses storyboard and last-frame reference images to lock the character design and art style across four timed shots.

This clip could not be loaded — it may have been removed from X.
SujiPop @suji_pop ·
View on X ↗

Prompt

Create an anime styled game cinematic animation. @image1 is the storyboard reference. 
@image2 is the last frame, follow the consistent character and artstyle as @image2

0:00-0:01: Close up shot: Empty surface of the roofttop, the girl’s foot enter frame and leave the frame. 

0:01 -0:03: Half body shot back view, camera following the girl as she sprinting on the rooftop, her ponytail hair flowing towards camera

0:03-0:06: Extreme long shot, in between two buildings, Silhouette of the girl and the wolf leap from one building to another, there’s a huge bright billboard of herself in the background. Slow mo when the girl is in between two buildings

0:06-0:10: Camera fast zoom out to the @image2 attached as the last scene. The animation in this scene is a looping idle animated game splash screen. Similar to those we can see in Honor of King, Overwatch or League of Legends. Long flowy hair animation, flickering billboards in the background, highly detailed. Consistent artstyle, background and characters. Cinematic, professional and dynamic camera angle.
? 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 10s.

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: "close-up", "tracking", "wide shot".
LIGHTING
"silhouette" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD
"cinematic, energetic" — Mood and aesthetic tone are explicitly directed to maintain emotional consistency throughout the scene.
DURATION
At 10s, 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 English. 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