Cinematic live-action dark fantasy, 30 seconds, 16:9, rainy midnight, neon city lights reflecting on wet streets, deep blue and violet color grade, realistic handheld camera, shallow depth of field, 24fps. Character: A young Japanese woman, long black hair, wearing a dark school-style coat, white shirt, black skirt, knee-high socks and black shoes. Keep the exact same face, hairstyle, body proportions and outfit throughout the entire video. Location: Empty Tokyo alley at night, wet asphalt, vending machines, glowing signs, abandoned bicycles, light fog and distant traffic. [0-4s] Wide establishing shot. The girl walks alone through the rain. Neon reflections shimmer across the wet pavement. Her footsteps echo through the empty alley. [4-7s] A strange black shadow appears behind her, moving independently from her body. She slowly stops and looks over her shoulder. Nothing is there. [7-11s] Close-up of her eyes. Violet light suddenly appears inside her pupils. The shadow on the ground stretches unnaturally toward the end of the alley. [11-15s] Three mysterious masked figures emerge from the fog and rush toward her. She remains completely still. Her shadow rises from the ground like liquid smoke. [15-19s] The shadow forms enormous wings behind her. As the attackers reach her, dark tendrils burst forward and throw them backward without blood or gore. Water splashes dramatically from the pavement. [19-23s] She slowly walks forward while the shadows move around her like living creatures. Streetlights flicker one by one behind her. [23-27s] Extreme close-up. She raises one hand. Every shadow in the alley suddenly points toward the sky. A powerful violet-black energy wave expands through the rain. [27-30s] Wide cinematic shot. The girl stands alone beneath the neon lights as the mysterious shadows disappear into the darkness. Rain continues falling. Camera slowly pulls backward. Cut to black. Style: Photorealistic live-action dark fantasy, anime-inspired supernatural atmosphere, realistic Japanese city environment, practical-looking VFX, volumetric fog, realistic rain, cinematic lighting, natural skin texture, detailed fabric, realistic physics, dramatic camera movement, subtle film grain, cinematic sound design. Negative Prompt: cartoon, anime 2D, obvious CGI, 3D render look, plastic skin, extra limbs, deformed hands, face morphing, identity drift, inconsistent clothing, duplicate characters, blurry face, flickering, jitter, text, subtitles, watermark, logo, gore, blood, low resolution, oversaturated colors.
This clip was generated with Seedance 2.5 by ByteDance. The prompt on this page is the exact text used to create it.
The example was generated with Seedance 2.5 using: 16:9 · 0:30 · Cinematic · Fantasy · Dark. Reusing these settings gives the closest match.
Copy the prompt as-is first, then change the subject while keeping the camera, motion, and lighting terms. Video models are sensitive to wording, so expect a few runs.
Yes. Prompts work best as starting points — swap scenes, adjust pacing terms, or change the aspect ratio to fit your project.