Dark Fantasy Evil Eye Character Close-Up

A text-to-video prompt that transforms an uploaded character reference into a supernatural dark fantasy presence with a glowing fiery orange evil eye. It uses an extreme close-up with a slow cinematic push-in and macro lens, keeping the character's identity locked to the reference image throughout.

This clip could not be loaded — it may have been removed from X.
BMX @bmx_ai13 ·
View on X ↗

Prompt

{ "title": "Evil Eye Character Animation", "type": "text_to_video", "duration": "6s", "aspect_ratio": "9:16", "reference_image": { "use_uploaded_image": true, "role": "main character reference", "instruction": "Use the uploaded image as the exact character identity, facial structure, costume, and overall visual reference. Keep the character consistent with the uploaded image throughout the shot." }, "style": "dark fantasy, supernatural, cinematic, high contrast, mystical energy", "scene": { "setting": "a deep dark void with subtle purple-black haze and glowing supernatural atmosphere", "mood": "ominous, haunting, powerful, mysterious" }, "character": { "description": "the main character is the uploaded image character, transformed into a supernatural evil-eye inspired presence", "consistency": "preserve the uploaded character’s face, identity, proportions, and recognizable details", "expression": "intense, hypnotic, threatening" }, "visual_design": { "eye_color": "#FF6F37", "background_color": "#060010", "glow_intensity": 0.35, "intensity": 1.5, "pupil_size": 0.6, "iris_width": 0.25, "scale": 0.8, "noise_scale": 1.0, "pupil_follow": 1.0, "flame_speed": 1.0 }, "camera": { "shot_type": "extreme close-up", "movement": "slow cinematic push-in", "focus": "sharp focus on the eye and character presence", "lens": "macro cinematic lens" }, "motion": { "primary_action": "the eye glows with fiery orange energy and organic flame-like motion", "secondary_action": "the pupil subtly tracks an unseen presence", "atmospheric_motion": "heat distortion, soft energy ripple, supernatural shimmer" }, "lighting": { "source": "the glowing eye acts as the main light source", "effect": "infernal orange glow illuminating the character in darkness" }, "prompt": "Use the uploaded image as the main character reference. The character from the uploaded image appears as a supernatural dark fantasy presence inside an evil-eye inspired cinematic scene. Preserve the exact identity, facial features, outfit details, and visual consistency of the uploaded image. The eye glows with fiery orange energy, with a hypnotic black pupil and molten flame-like textures moving organically inside it. The pupil subtly follows an unseen force, creating a sentient and threatening feeling. The background is a deep purple-black void with subtle haze, heat distortion, and supernatural atmosphere. Extreme close-up, slow cinematic push-in, dark fantasy aesthetic, high contrast lighting, smooth hypnotic motion, haunting mystical mood.", "negative_prompt": "different character, altered face, extra eyes, duplicate face, blurry details, cartoon style, low resolution, flat lighting, cheerful mood, washed out colors, text, watermark, logo" }
? 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 9:16 and clip duration to 6s.

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: "close-up", "macro".
LIGHTING
"low-key, dramatic lighting" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD
"eerie, mysterious" — Mood and aesthetic tone are explicitly directed to maintain emotional consistency throughout the scene.
DURATION
At 6s, 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