ffroliva/gflow-cli ? reverse-engineered prompt

Reverse engineered prompt

Build me a Python command line tool that lets me generate Google Flow images and videos from the terminal, plus an MCP server so coding assistants can control it too.

I want to be able to log into my own Google account once, then run simple commands to make text to image, text to video, image to video, and frame to video generations, all from scripts or batch jobs. It should save outputs locally by default, and also let me send them to cloud storage if I set a config value. I’d also like a way to extend a video past the normal limit, create reusable character references so the same person can appear across generations, and tweak prompts with a helpful creative rewrite mode.

Make it feel reliable for long runs, with clear status messages, easy authentication renewal, and good error handling when the Flow site changes. If you need to look up current docs online, do that.

Are you gonna build this?

make sure you review the code using coderabbit

Try freeSponsored — opens CodeRabbit in a new tab