Two Anime Girls Window Shop in a Photorealistic Mall

A 15-second cinematic sequence placing two locked anime-illustration characters into a fully photorealistic shopping mall, following them from arrival through window shopping to a joyful crane-out finale. The technique uses two reference images for strict character identity locking while the live-action environment stays realistic.

This clip could not be loaded — it may have been removed from X.
Toshi@ニャルオAI @Toshi_nyaruo_AI ·
View on X ↗

Prompt

Use Image A and Image B as the two main characters in all shots.

Image A : preserve her exact anime illustration identity, hairstyle, face, outfit, proportions, and overall design.

Image B : preserve her exact anime illustration identity, hairstyle, face, outfit, proportions, and overall design.

Both characters must remain anime-style illustrations with crisp clean line art, cel-shaded flat colors, expressive anime eyes, and zero photorealism on the characters.

All other elements — the shopping mall interior, storefronts, display windows, escalators, polished floors, shopping bags, crowd, lighting, and background architecture — are fully photorealistic.

Setting: a busy modern shopping mall on a weekend afternoon. Stylish interior, bright natural and commercial lighting, large glass storefronts, digital signage, polished floors, open atrium, many shoppers walking around. The atmosphere is lively, fashionable, and cheerful.

15-second cinematic video, 24fps, smooth motion, clear emotional flow, character consistency across all shots.

Shot 1 [MALL ENTRANCE — ARRIVAL]

Image A and Image B walk side by side into a crowded modern shopping mall, smiling and chatting. Many shoppers pass around them. The camera tracks backward in front of them as they enter the bright open atrium. They look excited for a fun day of window shopping.

Cut to Shot 2 [WINDOW SHOPPING — DISCOVERY]

The two girls stop in front of a stylish fashion storefront with a large glass display window. They lean in slightly and admire the items inside. Image A points at something cute in the display. Image B reacts with a bright smile and curious eyes. Medium shot, then close-up on their happy faces and pointing gesture.

Cut to Shot 3 [MOVING THROUGH THE MALL]

Image A and Image B continue walking through the busy mall, passing elegant shop windows, cosmetics counters, and accessory displays. They laugh together and casually gesture while talking. Camera moves alongside them. Background crowd flows naturally around them. Their mood is relaxed, lively, and playful.

Cut to Shot 4 [EXCITEMENT AT A DISPLAY]

They stop at another display window with fashionable accessories and seasonal decor. Image B notices something first and gently pulls Image A’s sleeve to show it. Image A’s expression changes into delighted surprise. Close-up on their faces, then cut to a wider shot showing both of them framed by the bright storefront and the bustling crowd behind.

Cut to Shot 5 [PURE WEEKEND JOY]

Image A and Image B continue window shopping deeper into the mall, each carrying a few small shopping bags. They smile, laugh, and enjoy the lively weekend atmosphere. Wide cinematic shot of the modern shopping mall interior, the two girls walking happily together at the center of the frame, surrounded by the photorealistic crowd and glowing storefronts. End with a gentle crane out
? 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 1:1 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
"tracking" is a core cinematic camera technique for establishing spatial immersion and subject framing. Also present: "crane", "close-up", "medium shot".
LIGHTING
"natural light, practical lights" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD
"playful, energetic" — 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