Anime Sticker Girl Fails on Arena Travelator

A flat 2D anime sticker character sprints up a steep conveyor-belt Travelator inside a realistic 1990s British arena game show, gradually losing ground and sliding off. The prompt mixes a paper-cut cartoon character with photoreal live-action arena footage, neon rigs, and a foam-waving crowd across five timed shots.

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

Prompt

{
  "style": "Authentic early-1990s British Saturday-night ITV broadcast style, realistic recreation of Gladiators arena footage, huge indoor arena with neon lighting rigs and foam-waving crowd, broadcast video texture with slight smear, electric atmosphere.",
  
  "main_character": "Q-version Anime Sticker Character with flat 2D sticker texture, bold cartoon outlines, and paper-cut feel. She has long golden hair with straight bangs and big purple round eyes. She wears a simple red and white athletic outfit with white helmet and knee pads. Her movements retain a slightly exaggerated, sticker-like quality while interacting with the realistic environment.",
  
  "shots": [
    {
      "time": "0-3s",
      "camera": "Wide arena shot",
      "description": "The Q-version anime sticker girl sprints toward the Travelator — a steep upward conveyor belt running fast downward against her. The crowd roars as neon arena lights sweep across the stage."
    },
    {
      "time": "3-6s",
      "camera": "Low-angle tracking shot",
      "description": "She leaps onto the belt and attacks it at full sprint. For a moment she gains ground, her long golden hair flowing as she pushes forward while the belt whines beneath her feet."
    },
    {
      "time": "6-9s",
      "camera": "Side medium shot",
      "description": "Her stride shortens — the belt wins. She’s running at full effort while slowly sliding backward, arms flailing, her big purple eyes shifting from focus to panic."
    },
    {
      "time": "9-12s",
      "camera": "Close action shot with motion blur",
      "description": "She drops to all fours and claws at the rubber surface, carpet-crawling desperately before getting dragged down and spat off the bottom onto the crash mat in a heap."
    },
    {
      "time": "12-15s",
      "camera": "Handheld follow shot",
      "description": "She lies on the mat, chest heaving, one arm raised in a hopeless thumbs-up as the buzzer sounds time-out. The Travelator keeps humming triumphantly behind her. Frame holds."
    }
  ],
  
  "technical_details": "High fidelity realistic live-action footage in the style of early-90s UK arena game show. Accurate conveyor-belt treadmill physics, neon arena lighting, and coherent character movement. The main character remains in flat 2D anime sticker style while the environment and physics stay realistic.",
  
  "negative_prompt": "blurry, low quality, deformed character, extra limbs, text, watermark, logo, overexposed, underexposed, modern artifacts, 3D rendered character"
}
? 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 2.39:1 and clip duration to 30s.

What makes this prompt work

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

CAMERA
"tracking" is a core cinematic camera technique for establishing spatial immersion and subject framing. Also present: "handheld", "low-angle", "medium shot".
LIGHTING
"neon" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD
"energetic, playful" — Mood and aesthetic tone are explicitly directed to maintain emotional consistency throughout the scene.
DURATION
At 30s, 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