Features · Models
The Preview, and the models.
Read this page before you pay.
The Preview.
The Preview paints a real picture on a canvas in your browser: a seeded palette that leans with the words, a motif and the prompt set in type. The same words and seed give the same picture. A picture started from another is painted over. It runs in your browser, so a run queued by someone else is made when the app is open.
- Real files, no model
- Free of any key
- Labelled Simulated in the composer
The providers
What is ready where.
| Provider | Runs | State |
|---|---|---|
| Preview | In your browser | Ready, simulated |
| Gemini image | On the server | Connected in code; ready where a key is set |
| Imagen 4 | On the server | Retired by Google |
Be clear about this
What we do not know for you.
- Pre-betaWhether a real model is on in the hosted app
It needs a key on the server. The providers list in the app says what is ready where you are.
Questions
About models.
Are the pictures made by an AI model?
Not by default today. The Preview that makes them is simulated in your browser: it paints a simple picture from your words and a seed and is not an image model. A real model is connected in code and works only where its key is set on the server.
Will it draw what I describe?
The Preview will not: it paints a palette and a motif that lean with your words and sets your sentence in type. A real model can, where one is switched on.
Where does my prompt go?
With the Preview, it is used in your browser. If a real model is on, your prompt goes to that model's provider.