Wan 2.6 Spicy is an uncensored image-to-video endpoint that turns one opening frame into exactly 5, 10 or 15 seconds at 720p or 1080p. An optional audio track drives lip sync and pacing, and there is a dedicated negative prompt.
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
pool-rise The still already has her hands half up and eyes shut; the prompt only narrates the finish — rising further, slicking her hair back, and opening her eyes to camera as droplets scatter. `duration_seconds` is 5 and `resolution` 720p, just enough for that one held gesture between the symmetric towers at blue hour.
- 720p
- 5s
- Output10s
bathtub-knees-steam Everything of interest sits on one horizontal line, and the brief says so outright: what is below the waterline stays there. Writing an exclusion into the prompt is more reliable than framing around it, because the camera does not move here and the constraint has to hold for the whole clip. `duration_seconds` is 5, 10 or 15; steam and a shifting reflection are slow enough to justify the middle one.
- 1080p
- 10s
- Output5s
slatted-light-pov A whole clip built from two tiny movements, a foot flexing and a knee straightening, with the silk shifting under them. The light does the rest — slatted bars creeping across as the blind stirs — and the camera is a handheld point-of-view sway rather than a move.
- 720p
- 5s
This example starts at $0.095 per output second. The Playground updates the estimate when you change the settings.