ai text "explain this code"              # generate text
ai image "a sunset over mountains"       # generate an image
ai video "a spinning triangle"           # generate a video
ai models --type image                   # list available models

-m, --model <id>       Model ID (provider/name or short name), comma-separated for multi-model
-o, --output <path>    Output file or directory
-n, --count <n>        Number of generations per model
-q, --quiet            Suppress progress output
--json                 Output structured metadata as JSON (paths, timing, success/failure)

# Pipe content in for summarization
cat file.txt | ai text "summarize this"
git diff | ai text "write a commit message"

# Image-to-video pipeline
ai image "a dragon" | ai video "animate this"

# Image editing via stdin
cat photo.png | ai image "make it a watercolor"

ai image "a sunset" --json

{
  "elapsed_ms": 3420,
  "count": 1,
  "results": [
    {
      "index": 1,
      "model": "openai/gpt-image-2",
      "elapsed_ms": 3420,
      "success": true,
      "file": "/path/to/output.png"
    }
  ]
}

ai image "a sunset" -m "openai/gpt-image-1,bfl/flux-2-pro,xai/grok-imagine-image"