
Medieval armoury: lacing a corset by torchlight
- Model
- Wan 3.0
- Task
- Text to video
- Resolution
- 720p
- Duration
- 5 s
- Aspect ratio
- 16:9
Output

This preview is blurred
This preview is marked sensitive. Confirm your age to see it.
PromptEN1104 characters
Photorealistic cinematic medium close-up, the camera close so she fills the frame from the hips up. A medieval castle armoury at night, a rack of swords and hanging mail on the stone wall behind her, burning wall torches the only light. An adult woman sits on the end of a fur-covered oak bench, long dark hair loose and damp at the temples, no helmet and no hood, wearing a loose cream linen chemise under a laced brown leather bodice. She pulls a long leather riding glove off with her teeth and drops it on the bench, then tightens the lacing at the front of the bodice, tips her head back against the cold stone and lets out a breath, eyes closing, then looks back down the lens. A torch beside her gutters and the shadows of the hanging swords swing across the stone. Slow push in from a low three-quarter angle, 85mm, shallow focus, hot orange torchlight raking across her shoulders against cold blue-grey stone, smoke drifting in the beam, 35mm grain. Audio: a leather glove slapping onto wood, the lacing creaking, the torch spitting and crackling, a chain swaying, her breath. No text, no logos.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
A period set carried entirely by practical firelight, and the clearest case on this page of writing sound into the same request: a leather glove slapping onto wood, the lacing creaking, the torch spitting. The framing is specified as well — hips up, low three-quarter — because a wide shot would throw all of that away.
Settings used
| Setting | Value | What it does |
|---|---|---|
| resolution | 720p | 480p, 720p or 1080p. Defaults to 720p. Resolution changes both the price and how long the task takes to come back. |
| aspect_ratio | 16:9 | 16:9, 9:16, 1:1, 4:3, 3:4 or adaptive, which lets the model choose. Defaults to 16:9. |
| generate_audio | true | On by default. The clip comes back with sound already locked to the picture. Set false when you are scoring the shot yourself. |
| duration_seconds | 5 | Any whole number from 2 to 30, or -1 for smart duration, where the model picks the length: the 30-second maximum is held up front and the charge settles on the length actually delivered. Defaults to 5. Longer clips drift more, so settle the look at 5 seconds before extending. |
More Wan 3.0 prompts
All Wan 3.0 prompts


Preview blurred



