10s2.35:1ZHJapanese Presenter Demonstrating Hand Gestures at Temple
A three-shot sequence featuring a presenter at an ancient temple courtyard, speaking Japanese dialogue with varying hand gestures and body movement. The camera slowly orbits in the first shot, stays static in the second, and follows her as she stands and walks in the third.
Jason W - AI @PocketScreenAI
Prompt (original, unmodified)
Image 1 speaks to the camera in the courtyard of a well maintained ancient temple. [0:00-0:05] Medium shot of Image 1. Camera slowly orbit as she says in Japanese with a gentle smile, "モノローグは棒立ちよりも少し体を動かすと自然に見えます。 [Cut: 0:05-0:10] Medium shot of Image 1 sitting on the steps of the temple. Stationary camera. She speaks in japanese, with subtle hand gestures, ”例えばこれを入れると手をセリフの一、二、三、に合わせて動かしてくれます。” [0:10-0:15] She slowly stands up and begins to walk slowly as she speaks with exaggerated hand gestures, in japanese, "大～きくとか、小っさくとか！うわっ！とか、ぜひ試して見てください。”
Reproduced verbatim from the original post. Never edited or translated. Everything outside this block is our own commentary.
How this prompt compares
The techniques this prompt uses are more common in character prompts than in the library overall:
| Technique | In character | Library average | Lift |
|---|---|---|---|
| static/fixed | 11% | 8% | 1.3x |
Across all 5,926 prompts, the techniques used here appear at: tracking 41%, orbit 14%, static/fixed 8%.
The 15s duration is not arbitrary: 71% of the prompts in this library that state a duration ask for exactly 15 seconds — Seedance 2.0 accepts clips up to 15 seconds, so 15s is the model's ceiling and the most common choice.
