Seedance 2.0 Prompt: Korean Baseball Stadium Spectator
Smiling Khan
Verified AI CreatorDescription
Generate an ultra-realistic candid KBO broadcast screenshot of a woman in a baseball stadium, retaining her exact facial identity with telephoto compression and motion blur.
TRY THIS PROMPT
video template
Use the uploaded reference image as the strongest identity anchor. The woman must look like the exact same adult woman from the reference image, not just a similar Korean woman.
Preserve her exact facial identity with high priority: same small oval face, same delicate jawline, same large clear eyes, same eye spacing, same eyelid shape, same straight nose, same soft muted pink lips, same pale clear skin tone, same refined calm expression, and same long black softly wavy hair.
Create an ultra-realistic candid KBO baseball broadcast screenshot of the same woman accidentally caught by a live TV camera in the spectator seats. The team name is LG and F1. Her face should remain closer to the reference image than to a generic stadium fan. Do not change her into another person. Do not make her face wider, older, sharper, more westernized, or more idol-like. Keep the same delicate studio-portrait identity, but translated naturally into a real stadium environment.
She is seated among a lively Korean baseball crowd, holding an iced drink and a cheering stick, wearing a clean white baseball jersey over a simple casual top. She is adjusting her hair with one hand .. She notices the camera and gives a small natural smile, slightly surprised but composed.
Use a realistic far-distance broadcast camera look: telephoto compression, mild video softness, slight motion blur in the crowd, stadium lighting, natural skin texture, imperfect candid framing, 16:9 horizontal TV broadcast composition.
Result
Download
Generations consume standard token rates depending on model specifications.
Prompt Specifications
Model Engine
bytedance/seedance-2.0
Output Format
854x480 •
15s
Verified Prompt FAQ
This prompt is used to generate AI video content with a ready-made technical structure,
model configuration, and reference image support. It helps creators test visual ideas faster
without building every prompt from scratch.
Yes. Upload your reference images inside the Prompt Tester panel on the right, then run the
generation test to preview how the prompt performs with your own visual direction.
Yes. This prompt is listed as a Synterial verified showcase prompt and includes its official
preview, model engine, output configuration, and testing workflow.