Anime Chase Through Magical Forest with Shih Tzu

A 30-second hyper-realistic anime chase sequence in the style of Makoto Shinkai, following a girl and her Shih Tzu fleeing giant thorny vines through a foggy magical forest. The prompt specifies a detailed timeline with a bullet-time dodge, a breakthrough into a sunny meadow, and a final panoramic pull-back, plus audio and consistency constraints.

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

Prompt

「緊迫の回避シーン」をAIで作ろうとしたら、物理法則を完全無視した爆笑動画が錬成されました😂
​避け方は百歩譲るとして、なんでその姿勢のまま草原の彼方まで吹っ飛んでくのww
よく見ると犬に押されてるように見えて腹筋崩壊した(笑)
​AI特有のこういう謎の暴走、たまらなく好きです。
元凶のプロンプトを公開しておきます👇
​Prompt
​Basic Settings
​Duration: 30-second short
​Aspect Ratio: 16:9 (Widescreen landscape format)
​Genre: Hyper-realistic cinematic anime chase sequence, Makoto Shinkai style.
​Setting: A terrifying, hyper-detailed magical forest. Photorealistic wet mud, moss, ancient towering trees, dense creeping fog.
​Style & Visuals
​Quality: Masterpiece cinematic anime, photorealistic environmental textures seamlessly blended with premium anime shading.
​Lighting: Dramatic contrast. Dark forest lit by toxic pulsating cyan/purple flora, sharp character rim lighting, transitioning into brilliant warm sunlight.
​Camera & Framing: Expansive horizontal tracking, wide anamorphic composition, sudden bullet-time macro close-up, sweeping panoramic pull-back.
​Consistency: Strictly maintain absolute visual consistency for Nako and Toto throughout.
​Audio & ASMR
​BGM: Fast-paced orchestral chase music, abruptly slows during bullet-time, transitioning into a peaceful acoustic melody at 22s.
​SFX: Whip-like snaps, running on mud, sharp "shing" in slow-mo, fading into gentle breeze and rustling grass.
​ASMR: Visceral heavy panting from Nako and Toto, softening into relieved sighs. NO voices, NO dialogue.
​Characters & Enemies
​Character 1 (Nako): Short brown hair, green explorer jacket, shorts, boots, backpack. Sweating, desperate expression.
​Character 2 (Toto): Fluffy white and tan Shih Tzu dog. Frantic sprint, ears flapping, panting wildly.
​The Thorns (Enemy): Sentient giant dark-green vines with razor-sharp glowing cyan/purple thorns, striking with terrifying whip-like speed.
​Timeline & Action
​0–10s (Wide High-Speed Chase): Immediate frantic sprint across the wide frame. Nako and Toto run at extreme speed. Glowing vines strike the ground violently behind their heels, splashing mud and debris toward the lens.
​10–15s (Bullet-Time Acrobatic Dodge): Sudden extreme slow-motion. A razor-sharp glowing thorn thrusts at Nako's face. She performs an acrobatic sliding backbend across the wide frame; the glowing tip grazes millimeters above her eyes, slicing a strand of hair. Toto slides fluidly underneath her.
​15–22s (The Breakthrough): Snapping back to high speed, they burst through the tree line into a vast, sunlit grassy clearing under a bright sky. The vines instantly recoil into the shadows.
​22–30s (Relief and Panoramic Pull-back): Nako collapses spread-eagle on the grass, smiling warmly at Toto. Toto sits beside her, panting happily with a wagging tail. The camera smoothly pulls back high into a breathtaking, silent panoramic wide shot of the sunny meadow and the distant forest edge.
​Negative Prompt / Constraints
​NO text, NO title, NO UI, NO logos.
​NO character morphing, NO outfit changes, NO breed changes.
​NO dialogue, NO human voices.
​NO slow pacing (except 10–15s bullet-time), NO camera jitter, NO distorted anatomy.
​#AIの暴走 #腹筋崩壊 #AI動画 #Seedance #生成AI #プロンプト公開
? 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 30s.

What makes this prompt work

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

CAMERA
"pull-out" is a core cinematic camera technique for establishing spatial immersion and subject framing. Also present: "tracking", "close-up", "wide shot".
LIGHTING
"rim light, dramatic lighting, volumetric" 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 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 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