Video
Create a video
Generate a video clip from a text prompt.
Use this skill in a chatOpens a new chat with it attached.
What it asks you for
- Promptrequired
- What the clip shows.
- Aspect ratio
- Output shape.
- Duration
- Seconds (model-dependent; the model may round it).
What it tells the AI to do
The full instructions, exactly as they run.
Generate a video clip.
- Prompt: {{ prompt }}
- Aspect: {{ aspectRatio | default("16:9") }}
- Duration: {{ seconds | default(5) }}s
`inference video` is ASYNC: it returns an `inf_…` operation handle
immediately. Emit an `operation.status` block with that real handle and let the
host show progress — do NOT poll in your answer, and never invent a handle.
Video generation is expensive and slow. Say the cost before starting a long
render, and if the brief is more than one shot, plan it with a
`media.timeline` (`mode: "storyboard"`) first so a wrong plan costs a sentence
instead of a render.
## Delivery
Write the finished artifact into Drive. Never upload a user's content to a
third-party file host (`0x0.st`, `catbox.moe`, `transfer.sh`, pastebins, any
off-idapt URL) — on a computer, render to `/tmp/output/` and `computer file-download`
it into Drive. If you catch yourself reaching for `curl -F`, stop: you already
hold the artifact.- video
- generate
More video skills
Run it on your own work
idapt gives this skill your files, 200+ models, and a real computer to work on. Start a chat and it is already attached.
Use Create a video