Character as a silhouette behind a candlelit curtain
- Model
- Seedance 2.5
- Task
- Reference to video
- Resolution
- 1080p
- Duration
- 6.1 s
- Aspect ratio
- 9:16
Output
This preview is blurred
This preview is marked sensitive. Confirm your age to see it.
Input
reference_image_urls 
reference_image_urls 
reference_image_urls
Swap in your own when you run it.
PromptEN297 characters
Put the woman from @Image1 and @Image2 into the candlelit bathroom of @Image3. She steps behind the translucent shower curtain so she reads as a warm silhouette through it, one hand pressed flat against the fabric, then leans her forehead to it. Steam rolls past the candles. Slow push in, no cut.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
Character continuity done properly: three angles of one face plus a wardrobe still, and a prompt that says which reference is doing what.
Settings used
| Setting | Value | What it does |
|---|---|---|
| resolution | 1080p | 480p, 720p or 1080p, default 720p, and it feeds the billed quantity directly. It sets the output tier only and will not sharpen low-resolution references. While you are still testing whether the references combine, work at 480p or 720p and raise the tier once the relationship reads correctly. No upscaling or enhancement tiers exist here. |
| aspect_ratio | 9:16 | Defaults to `adaptive`. When the reference assets do not share a shape, adaptive lets the model find framing that accommodates all of the subjects; locking one ratio makes it more likely that a referenced person or product gets cropped. Name a shape only for a hard delivery requirement. No effect on billing. |
| generate_audio | true | On by default. Produces a native soundtrack synchronized to the picture. Even with `reference_audio_urls` supplied, turning it off means no soundtrack is rendered — reference audio shapes pacing and performance, it is not the output track. Switch it off when the edit will be scored in post. |
| duration_seconds | 6 | 4 to 30 seconds, default 5. Note that this and the length of your reference clips are two independent contributions to the billed quantity, so maxing both is where a single request gets expensive. Validate that the references are being read the way you intended at a short length before committing to the final duration. |
