Dragon Flying Low Over Medieval City Breathing Fire

An image-to-video prompt that animates a reference image into a 10-12 second cinematic dragon flight sequence in the style of Game of Thrones. A dragon flies low over a medieval city's rooftops breathing turbulent fire that lights the stone buildings from below, while its rider leans forward with hair and cloak whipping in the wind. The prompt emphasizes photorealistic physics, volumetric smoke and embers, and synchronized audio.

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

Prompt

Faithfully animate this reference image into a breathtaking cinematic 10-12 second video in the exact visual style of HBO Game of Thrones and House of the Dragon epic dragon sequences. Maintain perfect consistency with the reference image — Daenerys' appearance, Drogon's anatomy, scales, wing structure, and initial lighting.

Drogon flies at high speed low over King's Landing rooftops with powerful, realistic wing flaps and body undulation. Massive turbulent fire breath erupts from its jaws, flames reacting dynamically to wind and movement with realistic fluid physics, glowing embers flying backward, intense heat distortion and light bloom. Fire dramatically illuminates the ancient stone buildings and Red Keep from below with shifting warm highlights and deep shadows.

Daenerys leans forward with commanding posture, her silver hair and heavy cloak whipping violently in the high-speed wind with realistic fabric dynamics and inertia. Subtle sparks and ash particles in the air.

Camera: Dynamic low-angle cinematic tracking shot that follows Drogon from a slightly behind and side position, moving at high speed with the dragon. The camera subtly rises and banks with the dragon's movement, creating a powerful sense of speed, scale and immersion. Sweeping, fluid camera motion with slight handheld energy mixed with controlled cinematic precision.

Physics: Highly realistic dragon wing membrane flexing and catching the wind, individual wing fingers moving naturally, heavy cloak and hair with authentic weight and turbulence, fire behaving with real fluid dynamics and interaction with air movement.

Lighting & atmosphere: Dragon fire provides the primary moving light source, dramatically lighting the city architecture from below. Volumetric smoke, embers and heat haze. Epic atmospheric depth with slight haze over the city.

Native synchronized audio: Deep powerful dragon roar mixed with the roaring whoosh of intense fire, strong wind rush, and distant city ambience with natural reverb. Photorealistic rendering, coherent motion, intricate detail, no artifacts, shot with ARRI Alexa-level fidelity. Masterpiece, maximum epic scale, speed, and cinematic impact.
? 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
"tracking" is a core cinematic camera technique for establishing spatial immersion and subject framing. Also present: "handheld", "low-angle".
LIGHTING
"volumetric, dramatic lighting, warm tone" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD
"epic, dramatic" — 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