Two women sharing a whisper in a jazz bar hallway
- Model
- Seedance 2.5
- Task
- Text to video
- Resolution
- 720p
- Duration
- 5 s
- Aspect ratio
- 16:9
Output
PromptEN442 characters
Warm, clearly lit close two-shot. Two adult women stand very close in the amber glow of a jazz bar's back hallway, one in a black velvet slip, the other in an open white shirt. One leans in and whispers something against the other's ear; the other closes her eyes and breaks into a wide laugh, then they rest their foreheads together. Handheld 35mm, warm practical lights, shallow focus, muffled saxophone, a whispered line and soft laughter.Written in English, exactly as we sent it.
Run this example
Checking the price…
Opens the playground with every setting filled in and shows the exact price before you run.
Same model, starting from this prompt. Other settings use their defaults.
Why this prompt works
The clip shown on this page, request and all: five seconds at 720p, 16:9, audio on. The wording deliberately carries the closeness through a whisper and touching foreheads, which passes where kissing wording does not.
Settings used
| Setting | Value | What it does |
|---|---|---|
| resolution | 720p | 480p, 720p or 1080p, default 720p, and it feeds directly into the billed quantity. Iterate on prompts at 480p or 720p and raise the tier only for the final take. The tier you pick is the tier the model renders at — there is no upscaling or enhancement step layered on top. |
| aspect_ratio | 16:9 | Defaults to `adaptive`, which lets the model choose the framing from the prompt — say "vertical short-form" and you will usually get a vertical composition. Lock a shape explicitly only when the delivery slot demands it (9:16 for feeds, 16:9 for landscape, 21:9 for widescreen); otherwise adaptive tends to compose more naturally. No effect on billing. |
| generate_audio | true | On by default. Produces a native soundtrack synchronized to the picture — voice, room tone, movement effects. Switch it off whenever the edit will carry its own music or narration: it stops the generated track from clashing with the one you add later. |
| duration_seconds | 5 | 4 to 30 seconds, default 5. The 30-second ceiling is the substantive change in this generation: a complete shot fits in one request instead of being chained together from closing frames. Length scales the billed quantity linearly, so confirm the motion and pacing at 5 seconds before going long. |
More Seedance 2.5 prompts
All Seedance 2.5 prompts
Romance on other models
Romance
Preview blurred