Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.appliedaifoundation.org/llms.txt

Use this file to discover all available pages before exploring further.

​
What it does

The Image Generator turns a text description into an image using AI image-generation models. It handles model selection, aspect ratio, resolution, and edit-an-existing-image flows in one consistent interface.

​
When to use it

  • “Generate image”
  • “Create a picture of…”
  • “Make me an image”
  • “Draw …”
  • “Generate artwork”

​
Models

ModelWhen to use
Nano BananaFast iteration, exploration, drafts
Nano Banana ProProduction-ready output, professional quality, strong text rendering inside the image (signage, labels, posters)
The skill prompts for model choice when the use case is ambiguous; for explicit “make a poster with this headline” requests it defaults to Pro because text rendering matters.

​
What you can control

  • Prompt — the description of the image
  • Model — fast vs professional
  • Aspect ratio — square, landscape, portrait, custom
  • Resolution — standard or higher
  • Reference image — optional, for edit-an-existing or style-transfer flows

​
How it works

  1. Captures the user’s description.
  2. Asks model and parameter preferences when they aren’t obvious from the request.
  3. Calls the image generation engine with the right configuration.
  4. Returns the generated image and the parameters used (so iterations are reproducible).
For edits (e.g. “the same image but change the background”), it accepts the original image as a reference input.

​
What it produces

  • The generated image in the requested aspect ratio and resolution
  • The exact prompt and parameters used (so the generation can be re-run or refined)
  • image-analysis — counterpart for analysing images instead of generating them