Korean Body-Horror Dolly Zoom in Junji Ito Style

A photorealistic K-horror scene of a middle-aged Korean man hunched on a worn sofa in a cramped Seoul apartment, his face showing bulging eyes and a silent scream with subtle spiral skin distortion. The camera performs a slow menacing dolly zoom inward on peeling walls with faint spiral patterns, using cold desaturated blue-green grading and harsh flickering fluorescent light. Over ten seconds the spirals on his face and surrounding objects intensify into unsettling crimson chaos.

This clip could not be loaded — it may have been removed from X.
Ƥ!ЖΣLƁΘUNCΣR @pixelbouncer ·
View on X ↗

Prompt

Cinematic ultra-photorealistic K-horror scene in Junji Ito disturbing manga style, average middle-aged Korean man in faded gray sweatpants and stained white t-shirt, hunched on worn sofa in cramped messy Seoul apartment, wide bulging eyes and silent scream with subtle spiral skin distortion on face, medium-wide eye-level shot with slow menacing dolly zoom inward on peeling walls with faint spiral patterns, cold desaturated blue-green color grading, harsh flickering fluorescent lighting mixed with deep ominous shadows, psychological body-horror isolation genre, ARRI Alexa 65 camera with 35mm anamorphic lens, subtle film grain, 16:9 ratio, hyperrealistic skin pores, fabric texture and decaying wallpaper details. (10 sec action: spirals on face and on objects intensify ther swirling and spinning up to an unsettling crimson k-horror chaos)
? How to use this prompt ▾
  1. Copy the prompt using the green "Copy prompt" button above.
  2. Open your model — launch Grok Imagine 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 10s.

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", "medium shot".
LIGHTING
"low-key, cool tone" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD
"surreal, eerie" — Mood and aesthetic tone are explicitly directed to maintain emotional consistency throughout the scene.
DURATION
At 10s, this clip is optimized for high temporal coherence and fluid, realistic motion physics.
MODEL
Grok Imagine (xAI) 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