Turn words and reference images into videos.
Creates and edits videos from text, images, or reference footage using Wan and HappyHorse models.
When to use it
Use for requests to generate, animate, or edit videos, not for image generation or analysis of existing videos.
Give it a video creation or editing request; it submits the generation task, waits for completion, and downloads the video.
The default script requires Python 3.9 or newer and uses only the standard library.
Requires a QianWen account with an API key; some models must also be enabled on the account.
This skill
DashScope
Starts billed video generation (irreversible)
Sends prompts and reference media
OSS
Uploads media to your OSS