Girl and Shiba Inu Play in a Summer Japanese Garden

A 15-second cinematic sequence showing a young Japanese woman and a Shiba Inu playing together on a traditional wooden veranda and garden. The prompt uses shot-by-shot timing, warm golden-hour-style lighting, and detailed consistency constraints to keep the character and animal stable throughout.

This clip could not be loaded — it may have been removed from X.
Cia0 @Cia0_exe ·
View on X ↗

Prompt

Visual style: Cinematic high-quality realistic illustration style, warm natural sunlight, dramatic soft lighting, shallow depth of field, light film grain, golden color grading, no AI artifacts, no glitch, physically accurate human and animal biomechanics\n\nTotal duration: 15s\nAspect ratio: 16:9\nFPS: 24fps\n\nJapanese woman, 24 years old, natural warm appearance, black hair in a loose low ponytail with soft flyaway strands, gentle sun-kissed skin tone, genuine bright smile, light natural makeup, wearing a breezy pastel linen sundress suited for hot summer weather, barefoot on wooden veranda, relaxed candid body language, character remains consistent and fully visible throughout, no disappearing, no morphing, no warping\n\nANIMAL:\nShiba Inu, classic orange-red fur with white chest and face markings, perky upright ears, curled fluffy tail, bright expressive eyes, natural \"shiba smile\", energetic playful movement, physically accurate animal biomechanics, no stiff or robotic motion\n\nSETTING:\nTraditional Japanese home garden with wooden engawa veranda, small green garden with potted plants, wind chime (furin) hanging and swaying gently, bright clear blue sky, midday sunlight, dappled komorebi light through tree leaves, warm summer atmosphere\n\nSCENE BREAKDOWN:\n\n0-1.5s (HOOK): Shiba Inu bursts joyfully into frame running toward girl, ears flopping, tail wagging fast, motion blur on legs - girl turns and laughs genuinely, caught mid-motion\n\n1.5-4s: Girl crouches down laughing, dog jumps up excitedly, playful nose-nudge and paw-tap interaction, warm sunlight glinting on fur\n\n4-6.5s: Girl playfully tosses a small toy off-frame, dog dashes after it with comedic energy, grass particles kicked up, tracking shot following the chase\n\n6.5-8s (SOUND SPIKE): Dog catches toy, shakes head triumphantly, happy bark quick whip-pan to extreme close-up on dog's joyful face\n\n8-10.5s: Girl sits on veranda, dog runs back and nuzzles into her lap, girl's surprised delighted laugh, close-up on this warm connection moment\n\n10.5-13s: Dog tilts head endearingly, girl scratches behind its ears, wind chime rings softly in the breeze, brief slow-motion (1s) on the eye-contact moment between them\n\n13-15s (ENDING): Freeze frame girl and dog looking toward camera together, warm genuine smile, golden natural light, soft fade to black\n\nVISUAL EFFECTS:\nmotion blur trailing on fast dog movement, dust/grass particles catching sunlight, lens flare through tree leaves, fabric of dress billowing naturally in breeze, light film grain, shallow depth of field on close-ups\n\nAUDIO DESIGN:\n\n0-1.5s: ambient garden birds + cicada (semi) sound + sudden excited dog bark (sound anchor)\n\n1.5-6.5s: light acoustic/ukulele background music building + genuine laughter + dog panting\n\n6.5-8s: sound spike triumphant bark / toy squeak\n\n8-13s: music softens, warm tone, gentle furin wind
? 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
"pan" is a core cinematic camera technique for establishing spatial immersion and subject framing. Also present: "tilt", "tracking", "close-up".
LIGHTING
"soft light, natural light, warm tone" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD
"playful" — 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