# Use AI Pics with your AI

> Connect Claude, ChatGPT or Grok to AI Pics through Geenius OS: it queues picture runs, reads results and manages collections. A page makes them.

Source: https://aipics.geenius.io/docs/use-with-your-ai/

AI Pics has no AI you must use, and today its pictures come from a simulated Preview. Your own AI, Claude, ChatGPT or Grok, can queue picture runs, read the results, list and favourite pictures and keep collections through Geenius OS. **A page makes the pictures**: a run is made when somebody has AI Pics open.

> [!HONEST]
> The Preview provider is simulated in a browser: it paints simple pictures from your words and a seed, and it is not an image model. Real image models are connected in code and ready only where their keys are set. Making pictures is on Premium and Max; Pro is the library. The door is on every plan, and during early access people request access.

## Connect it

Add AI Pics to your Geenius OS workspace and connect your AI to Geenius OS once, by the steps in the Geenius OS docs. Your AI then has tools called `picture` and `collection` of `geenius_geeniuspics`.

## How a call looks

```json title="See what can make pictures here"
{ "tool": "picture", "action": "providers", "args": {} }
```

## Your first ask

```text title="A first ask"
Use Geenius OS and AI Pics. Ask which providers are ready, then queue one run of two square pictures of "a lighthouse at dusk" with the Preview, and tell me the run id. Then tell me to open AI Pics so it gets made.
```

## The tools

::mcp-tools

Ask for the actions with `action: "help"`, and for one action with `of`.

## Habits that work

- **Ask for providers first.** `providers` says what is ready.
- **Queue, then say who makes it.** Tell the person to open the app.
- **Use seeds.** The same words and seed give the same Preview picture.

## What your AI cannot do

It cannot make a picture without an open page for the browser Preview, and it cannot make one on Pro. It does not promise a result: the Preview is a simulation.