Wan 2.7 Spicy is an uncensored image-to-video endpoint that turns one opening frame and a prompt into 2 to 15 seconds at 720p or 1080p. It generates audio or follows your own track for lip sync, with a negative prompt and no content declaration.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Output5s
surf-silk-scarf Wind and water on thin fabric: the breeze pulls a long silk scarf out behind her and ripples her ivory dress as she turns to the camera, while surf rushes round her ankles. Three things move to three different rhythms, which is harder than a person simply turning round.
- 720p
- 5s
- Output5s
backstage-mirror-turn The `prompt` sequences four beats — adjusting the strap, checking the mirror, turning to camera, stepping toward the stage — so the model gets a finish line, not an open gesture. `image_url` fixes the bulb-lit mirror, sequins and feathers in frame; words add motion and sound: bulbs flickering, orchestra through the wall. `duration_seconds` `5`, `resolution` `720p`, lands it.
- 720p
- 5s
- Output5s
dune-silk-throw Several metres of loose silk thrown overhead and turned under, on a dune, at night, in wind. Large soft fabric is where most video models tear or freeze, and there are three other moving things around it — sand streaming off the crest, a guttering lantern flame and her long shadow across the ripples.
- 720p
- 5s
This example starts at $0.123 per output second. The Playground updates the estimate when you change the settings.
