1 / 2
Seeddance 2.0FORMAT:
视频
1.9K 1

FORMAT:

ᴍ

By

ᴍᴜʀᴘʜʏ

Prompt

VIDEO · 1

FORMAT: 16:9 cinematic storyboard presentation, 1920×1080, ultra-detailed high-resolution STYLE: Hyper-realistic YouTube livestream horror, premium storyboard infographic, cinematic found-footage realism, dark documentary aesthetic PROJECT: PARIS CATACOMBS LIVESTREAM TITLE: “LIVE EXPLORING PARIS CATACOMBS (NOT CLICKBAIT)” DURATION: 15 Seconds LAYOUT: 5 large cinematic storyboard frames in top row Technical breakdown panels in bottom row Black premium background Thin white borders Red YouTube LIVE accents Minimal professional production-board layout ──────────────────── FRAME 01 (0:00–0:03) STREAM STARTS Wide handheld selfie shot. Streamer walking through narrow Paris catacombs tunnel. Walls built from skulls and bones. Headlamp and flashlight are only light sources. YOUTUBE UI OVERLAY: LIVE ● Viewers: 18,492 Chat visible on right side CHAT: “bro this is illegal” “turn back” “no way this is real” CAMERA: Handheld selfie cam Slight shake VISUAL: Wet stone walls Skulls Dark tunnel depth ──────────────────── FRAME 02 (0:03–0:06) DEEPER INSIDE Rear-facing camera. Tunnel becomes tighter and more claustrophobic. Streamer scans walls using flashlight. DIALOGUE: “Guys… I don’t think tourists come here.” CAMERA: Sony A7S III low-light look Shaky tracking shot VISUAL: Bones everywhere Moisture on walls Water puddles ──────────────────── FRAME 03 (0:06–0:09) CHAT NOTICES SOMETHING Streamer pans camera. Nothing visible to him. Chat suddenly floods rapidly. CHAT: “WAIT” “WHO IS THAT” “BRO BEHIND YOU” “RUN” CAMERA: Fast pan Digital compression artifacts VISUAL: Bitrate drop Glitch tearing Audio waveform distortion ──────────────────── FRAME 04 (0:09–0:12) ENTITY APPEARS Camera slowly turns toward deep tunnel. Far away: Tall pale humanoid figure. Standing completely motionless. No visible face. Unnaturally long limbs. CAMERA: Slow digital zoom Compression noise VISUAL: Flashlight flicker Deep darkness Entity silhouette ──────────────────── FRAME 05 (0:12–0:15) STREAM ENDS Entity suddenly much closer. Impossible movement. Streamer screams. Camera drops sideways. Final frame: Entity crouching near fallen camera. YOUTUBE UI: SIGNAL LOST STREAM ENDED VISUAL: Static noise Broken stream frame Corrupted pixels ──────────────────── KEY VISUALS: - Catacomb skull walls - YouTube live UI - Chat overlay - Flashlight beam - Compression artifacts - Pale humanoid entity - Moist tunnel reflections - Broken stream signal CAMERA STYLE REFERENCE: - IRL YouTube livestream - GoPro + Sony low-light footage - Found footage horror - Handheld realism - Sensor noise - Rolling shutter artifacts LIGHTING: - Headlamp beam - Flashlight spill - Cold blue shadows - Black void darkness - Moisture reflections - Flickering light COLOR PALETTE: Deep Black Bone White Wet Stone Gray Cold Blue Emergency Red AUDIO REFERENCE: - Dripping water - Heavy breathing - Footsteps - Chat notification pings - Digital glitch distortion - Sudden silence IMPORTANT NOTES: - Must feel REAL, not cinematic-polished - Zero supernatural glow - Entity should be subtle and terrifying - Horror comes from realism - Authentic livestream imperfections required TONE & ENERGY: Claustrophobic Unsettling Viral horror Psychological dread Realistic panic OUTPUT: Premium horror livestream storyboard Feels like a real viral YouTube stream gone horribly wrong

Prompt structure analysis

This 视频 prompt uses about 3383 characters across 157 descriptive segments. It builds the shot around “FORMAT:” and explicitly controls camera, lighting, action, visual style, audio, setting.

Control dimensions detected

CameraLightingActionVisual styleAudioSetting

How to adapt it

  1. Replace the main subject or setting in “FORMAT:” while preserving the original action logic.
  2. Keep the camera instruction and change only its speed, direction, or framing.
  3. Generate a baseline, then change one variable at a time to compare motion, consistency, and pacing.

More inspiration

Seeddance 2.0Epic anime battle scene, fierce young man warrior with b...

Epic anime battle scene, fierce young man warrior with b...

Seeddance 2.0Ultra wide cinematic aerial shot during blue hour over th...

Ultra wide cinematic aerial shot during blue hour over th...

Seeddance 2.0Cinematic Gaming Short with Seamless Transitions

Cinematic Gaming Short with Seamless Transitions

Seeddance 2.0Masterpiece, best quality, official anime character desig...

Masterpiece, best quality, official anime character desig...

Seeddance 2.0Main subject: young American woman, early 20s, natural ev...

Main subject: young American woman, early 20s, natural ev...

Seeddance 2.0Stylized 3D animation with exaggerated cartoon proportion...

Stylized 3D animation with exaggerated cartoon proportion...

Seedance 2.0 prompt examples that show the result

Each example pairs reusable prompt text with a playable video, so you can judge camera motion, pacing, lighting, subject consistency, and visual style before generating.

From prompt idea to AI video in one workflow

Choose a prompt, refine the scene, add a reference image when needed, then set aspect ratio, resolution, duration, and audio in the side generator.

How to write a stronger Seedance video prompt

Describe the subject, action, setting, camera movement, framing, lighting, visual style, and timing. Keep instructions concrete and remove details that do not change the shot.