What it’s about
It started with two consoles, one per provider. Whatever I generated there was fleeting: an image stayed wherever it had been made, and from the next device I could not get at it. At some point that bothered me enough.
The ai-image-generator puts both providers behind the same interface and the same API. I pick a model, set the aspect ratio and the quality level, and optionally hand over reference images for the result to follow. The library is searchable by prompt and filterable by model, ratio and favourite. What an image cost is something both providers report themselves; it is kept and can be broken down by month and model.
These days I mostly don’t even open the interface. A Claude skill hands the prompt and reference images straight to my own API, and by the time I’m back in the session the finished image is already waiting. Installed as a plugin, it can do everything the interface can.





