gpu video create

Create a video generation job

Synopsis

Submits a video generation job. With --wait>0 the CLI polls the job until it reaches a terminal status (completed/failed/expired/cancelled); --wait=0 (the default) returns the queued job immediately so you can track progress with gpu video get and fetch it later with gpu video download.

gpu video create [flags]

Examples

# Submit and return immediately
gpu video create --model gpuai/wan-2.2-t2v --prompt "a timelapse of clouds over mountains"

# Set the clip length (each model declares its bounds + default in
# `gpu models get <id>`; omitting --seconds uses the model default)
gpu video create --model gpuai/wan-2.2-t2v --prompt "ocean waves at sunset" \
  --seconds 5

# Block until the job finishes (poll up to 10 minutes)
gpu video create --model gpuai/wan-2.2-t2v --prompt "city traffic at night" --wait 10m

Options

  -h, --help               help for create
      --model string       Video model id (e.g., gpuai/wan-2.2-t2v) — required
      --prompt string      Text prompt describing the video — required
      --seconds int        Desired video length in seconds (bounds + default come from the model's catalog entry)
      --size string        Video size as WxH — only for models that declare a size parameter; most live video models generate at their default resolution and reject --size
      --wait duration      How long to poll the job for a terminal status; 0 = don't poll, return immediately

Options inherited from parent commands

      --api-base string   API base URL (override with GPUAI_API_BASE env) (default "https://api.gpu.ai/v1")
      --debug             Enable debug logging to stderr
  -o, --output string     Output format: table|json (default table on TTY, json otherwise)

SEE ALSO

• gpu video - Generate and manage videos