Weightless underwater ballroom in an emerald gown
- Model
- Seedance 2.5
- Task
- Image to video
- Resolution
- 720p
- Duration
- 5 s
- Aspect ratio
- adaptive
Output
Input
image_url
Swap in your own when you run it.
PromptEN487 characters
Everything is weightless underwater. The camera drifts in a slow orbit around her as she turns in the water; the emerald gown unfurls in a long slow spiral, her hair fans out and the gold dust swirls in her wake. The chandelier sways above her and its god rays sweep across the flooded ballroom, long chains of bubbles rising past the lens. She tips her head back, opens both arms and rises slowly toward the light. Slow weightless orbit, deep teal and gold, muffled underwater ambience.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 still fixes a whole ballroom underwater with the chandelier still burning and a figure weightless at the centre of it. The prompt takes over the weightlessness itself: the gown unfurls, the gold dust draws a ring, and she opens both arms and rises toward the light. This one is vertical, so set beside the two wide clips it shows what adaptive does — the output follows the aspect ratio of the first frame.
Settings used
| Setting | Value | What it does |
|---|---|---|
| resolution | 720p | 480p, 720p or 1080p, default 720p, and it feeds the billed quantity directly. Note that the output tier is independent of the source still: a soft low-resolution frame rendered at 1080p is just enlarged softness. The tier you pick is the render tier, with no upscaling or enhancement layered on top. |
| aspect_ratio | adaptive | Only `adaptive` is accepted here: Seedance 2.5 always frames an image-to-video clip on the geometry of the opening frame, and a fixed shape would make the task fail. If the delivery format is fixed, crop or pad the still to it before you send it. No effect on billing. |
| generate_audio | true | On by default. Produces a native soundtrack synchronized to the picture — room tone, movement effects, voice. Turn it off for product pieces that will be scored in post; leave it on when footsteps and ambience are part of the point. |
| duration_seconds | 5 | 4 to 30 seconds, default 5. The longer a frame-driven shot runs, the more it drifts — anatomy and set dressing deform gradually. Confirm the direction of the motion at 5 seconds, then extend. For genuinely long sequences, several shorter takes cut together usually hold better than one 30-second take. Length scales the billed quantity linearly. |
