Your AI assistant generates images for you
Two commands. That's it.
Plus --model, --aspect, --dimension, --output, and more. Run masonry --help for everything.
50+ models, one CLI
Frequently asked questions
Masonry CLI generates AI images and video from your terminal across 50+ models, including Veo 3, FLUX, Imagen 4, and GPT Image 2. It works with Claude Code and other AI coding agents, so an agent can create an asset mid-session without leaving the terminal.
- Can Claude Code generate images?
- Not on its own. Claude Code is a text coding agent with no built-in image model. With the Masonry CLI installed, you can ask it to generate an image in plain language and it runs the command for you, saving the file into your project.
- How do I generate an image from the terminal?
- Install the CLI with npx @masonryai/cli, run masonry login to connect your account, then run masonry image "your prompt". The image saves to your current directory. Use masonry video "your prompt" for video.
- Which AI models does the Masonry CLI support?
- Over 50 image and video models, including Veo 3, FLUX, Imagen 4, GPT Image 2, Nano Banana, Kling, and Seedance. Pick one with the --model flag, or use the default.
- Do I need an API key?
- No raw provider keys. You authenticate once with masonry login, which connects the CLI to your Masonry account, and generations draw from your account balance.
- Does it work with other AI coding assistants, not just Claude Code?
- Yes. The CLI is a normal shell command, so any agent or tool that can run shell commands, or a project skill that wraps it, can call it. No special integration is required.
- What can I control on a generation?
- Model (--model), aspect ratio (--aspect), dimensions (--dimension), and output path (--output), plus more. Run masonry --help for the full list.
Get started in seconds
Need an account? Sign up free
