Create a storyboard in a 3×3 grid format. studio ghibli style. female elf defeating a monster. Use reference image to create a 15s cinematic fantasy animation.
Chi tiết nhắc nhở
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.
How to work from this case
- Start with the original prompt and identify which subject, camera, and mood phrases drive the output.
- When iterating, change one variable first: lighting, motion, or emotion.
- If references are involved, adjust framing and movement separately for more stable generations.
Editorial handling note
Public prompt pages show edited case notes instead of copy-ready raw text. High-risk, explicit, and brand- or likeness-sensitive entries are filtered from the public library.
Related Seedance prompts
戦闘中に彼女が覚醒するシーン。 シーン 1：廃墟の地面。彼女の手元のクローズアップ。セリフ：「誰をゴミ呼ばわりしてるの？」。悔しさで震えながら土を握りしめる。 カット切り替え。 シーン 2：斜め後方上空からのショット。うずくまる彼女。セリフ：「なめないで」。彼女からオーラが溢れ出す。ゆっくりと立ち上がる。顔や表情は見えない。 カット切り替え。 シーン 3：彼女の顔のクローズアップ。顔の半分が影に覆われている。セリフ：「許さない」…
Fast-paced POV helmet-camera footage of a skateboard rider rapidly dropping into a short wooden backyard half-pipe ramp, immediate acceleration down the curved wooden surface with realistic gravity and wheel vibration,…
Continue browsing Seedance content
After a single prompt, the next move is usually another example from the library or a guide and glossary entry that add method and terminology.
Prompt Library
Return to the prompt library to keep narrowing
Compare structure, media setup, and control patterns across examples.
Duyệt qua
Guides
Read guides for the underlying method
Turn isolated examples into reusable workflow patterns.
Duyệt qua
Glossary
Use the glossary to complete the control language
Clarify camera, reference, and consistency language before the next iteration.
Duyệt qua