imager

What it is good at

• The draft loop, which is the whole point

  A low-quality draft costs about $0.006 against about $0.053 for a high-quality final on the default model, so the workflow generates a draft, shows it to you, and only spends the real money once you have said yes. Finding a direction across a ten-slide carousel costs $0.06 rather than $0.53, and the approved draft can be passed back as a reference image to hold the composition.

• Telling you the cost before it spends it

  Every run is estimated first, the way OpenAI bills it: prompt text, input images and output image, each at its own token rate. Below $0.50 it proceeds; at or above, it stops and asks. A batch file of many images is priced and confirmed once, one flag prices a run without generating anything, and another prints the fully assembled prompt without making a request at all. A tool that spends your money should never surprise you about how much.

• No dependencies, and no vendor SDK

  The standard library only, so it runs on the system python3 straight from a plugin install, with no setup step. The API calls go out over urllib. That is a deliberate trade: this is a skill that holds an API key, and the less third-party code sits between the key and the wire, the less there is for you to audit before you trust it.

• Presets that carry the whole prompt, not a style word

  27 of them, each pairing a short description you choose from with a full prompt fragment that does the work - editorial, blueprint, ink, risograph, wireframe, brutalist and more for visual work, and a separate set for infographics, slides, diagrams and posters where the text inside the image has to be legible. Platform sizing covers the eight places images go.