Cel-Shaded Anime Fighter Psychic Avatar Super on Neon Rooftop

A 22-second cel-shaded 2D anime fighting game cinematic in which a silver-haired girl summons a psychic energy avatar for a special move against an opponent on a neon-lit rooftop, framed with arcade HUD overlays, action lines, and a multi-cut K.O. finish.

This clip could not be loaded — it may have been removed from X.
yachimat - AI Short Anime @yachimat_manga ·
View on X ↗

Prompt

# ═══════════════════════════════════════════════
# PROJECT: 2D Fighting Game Sequence
# SPECS: Playstation 4 / 30FPS / Budget 500M JPY
# ═══════════════════════════════════════════════

visual_config:
  style: >
    2D anime-style fighting video game screenshot,
    cel-shaded, bold outlines, gold-purple-crimson palette,
    manga-style dynamic lines, arcade game aesthetic

character_settings:
  player:
    girl: "@Image1"
    avatar: >
      psychic energy avatar, translucent golden humanoid fencer,
      Silver armor plates, glowing cyan eyes,
      appears behind user as spiritual projection
  opponent: "@Image2"

timeline:
  cut_01:
    dur: 6s
    shot: side view full shot
    prompt: >
      stylized 2D fighting video game interface,
      health bars and timer HUD overlay,
      hit counter UI incrementing,
      silver-haired girl performing rapid energy strikes,
      bright golden light effects on each motion,
      dynamic action lines radiating outward,
      special meter gauge filling up,
      neon-lit urban rooftop night stage background,
      arcade game screen composition
    cam: static side view, light screen shake on impacts

  cut_02:
    dur: 3s
    shot: extreme close-up, diagonal screen transition
    prompt: >
      sudden dramatic insert shot,
      screen splits with diagonal wipe transition,
      girl's face in extreme close-up filling frame,
      golden eyes with subtle glow, bold confident grin,
      ink-style shadows across one side of face,
      purple-gold energy aura behind head,
      abstract crimson dynamic lines in background,
      game UI text indicating special activation
    cam: instant snap zoom, tilted angle

  cut_03:
    dur: 5s
    shot: behind girl, over-the-shoulder
    prompt: >
      girl standing arms spread wide seen from behind,
      large translucent psychic avatar rising behind her,
      twice her height, golden armored plates catching light,
      expanding ring of purple-gold energy particles,
      opponent stepping back across the arena,
      background distorts with heat-shimmer effect,
      glowing particles orbit both girl and avatar,
      strong backlight creating dramatic silhouette,
      video game special move activation sequence
    cam: slow dolly in, low angle

  cut_04:
    dur: 8s
    shot: rapid multi-angle montage
    prompt: >
      avatar performs rapid successive energy projections,
      screen filled with overlapping golden light trails,
      cascading visual effects layering dynamically,
      final powerful motion sends energy wave forward,
      full-screen white flash transition,
      large stylized game UI "K.O." text appears with glass-particle burst effect,
      hit counter displays high number,
      opponent life gauge reaches zero,
      video game finishing sequence animation
    cam: rapid angle changes, final moment in slow motion
? 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 16:9 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
"dolly" is a core cinematic camera technique for establishing spatial immersion and subject framing. Also present: "zoom", "orbit", "static/fixed".
LIGHTING
"backlight, neon, silhouette" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD
"energetic, dramatic" — 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 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