Create a 20-second cinematic, ultra-realistic AI video featuring a young Korean woman with long, dark, slightly wavy hair, wearing a white blouse and dark pants. Begin with a close-up of her sitting beside a window, looking thoughtfully at her smartphone in soft natural daylight. Transition to an outdoor zoo setting where she stands near a railing, casually using her phone while observing the surroundings. Show her approaching the lion enclosure and raising her smartphone to capture a photo of a majestic lion below. Suddenly, the lion charges toward her, creating a tense and unexpected moment. She drops her phone and struggles to escape as the lion lunges at her inside the enclosure. Capture her frightened expressions, realistic body movements, flying dust, and the lion's powerful motion. Use dynamic camera angles, smooth cinematic transitions, natural sunlight, realistic shadows, and detailed environmental textures. Maintain consistent facial features, hairstyle, clothing, and body proportions throughout the video, with dramatic pacing and photorealistic quality.
This clip was generated with Seedance 2.0 by ByteDance. The prompt on this page is the exact text used to create it.
The example was generated with Seedance 2.0 using: 16:9 · 0:20 · Dramatic · Cinematic · Realistic. 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.