Cyberpunk night subway ride in a chrome puffer
- Model
- Seedance 2.0
- Task
- Text to video
- Resolution
- 720p
- Duration
- 5 s
- Aspect ratio
- 16:9
Output
PromptEN520 characters
Photorealistic live action, not animation. Neon cyberpunk night ride on an almost empty subway carriage. A real adult woman in a cropped chrome-silver puffer jacket worn open over a black high-neck bodysuit and sheer tights stands holding the pole, swaying with the carriage; magenta and cyan tunnel lights strobe across her face. She catches her own reflection in the dark window, tilts her head and smiles. Anamorphic flare, rain-streaked glass, wet vinyl seats, deep blue shadows. No music, only ambient train rumble.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 second clip on this page, request and all. Worth knowing why generate_audio is off: the first attempt named music in the scene and the model's own layer refused to render a soundtrack on music-rights grounds, with nothing billed. Re-running it silent went straight through — if a prompt implies recognisable music, plan to score it yourself.
Settings used
| Setting | Value | What it does |
|---|---|---|
| resolution | 720p | Output resolution, 720p by default and reaching 4k; no upscaled tier is offered on this endpoint. It sets a rate tier, and higher tiers mean bigger files and longer renders. Draft at 480p and raise it only as far as the delivery needs. |
| aspect_ratio | 16:9 | Output framing, `adaptive` by default: the model picks the shape the prompt describes — ask for a vertical short-form shot and it usually composes vertically. Six fixed ratios are there for when the placement format is already decided. No effect on billing. |
| generate_audio | false | Whether a native soundtrack is rendered in sync with the picture. On by default; switch it off when you need picture-only material to score or dub later. |
| duration_seconds | 5 | Length in whole seconds, 4 to 15, defaulting to 5, and the billed quantity. Pass -1 and the model picks the length itself: the estimate assumes the 15-second maximum and the final charge follows the delivered length. The extra seconds over the previous generation are room to finish an action, not licence to cram in a second idea; longer pieces are cut together from several takes. |
