Inline preview
Generated images and video frames display directly in your terminal using the Kitty graphics protocol. Supports Kitty, Ghostty, WezTerm, Warp, and iTerm2.
A tiny CLI for generating text, images, and video with dead-simple commands. Pipe content in and out. Compare models side by side. See results inline.
Run the same prompt across multiple models in parallel. Compare outputs side by side to find the best result. Combine with -n to generate multiple per model.
Pipe text in as context, pipe images into video generation, chain commands together. Raw output on stdout when piped, file saves when interactive.
Access text, image, and video models from OpenAI, Anthropic, Google, Black Forest Labs, ByteDance, and more through Vercel AI Gateway.
Not a chatbot. A generation tool that fits into any workflow — scripts, CI pipelines, agent toolchains, or just your terminal.
Generated images and video frames display directly in your terminal using the Kitty graphics protocol. Supports Kitty, Ghostty, WezTerm, Warp, and iTerm2.
Predictable behavior for scripts and agents. Raw stdout when piped, file saves when interactive. JSON metadata mode for CI pipelines.
Models are fetched directly from the AI Gateway — no hardcoded lists to maintain. Use short names or full provider/model IDs.
No config files, no init command, no setup wizard. Set an API key environment variable and start generating. Defaults work out of the box.