Generate Your First Image

This walks you through creating a board, writing a prompt, and generating an image.

1. Create a board

From the dashboard, click New Board. Give it a name (or accept the default) and you’ll land on an empty canvas.

2. Add a prompt node

Right-click anywhere on the canvas (or use the + button in the toolbar) and add a Prompt node. Type what you want to generate, for example:

A black-and-white film still of a fox sitting on a windowsill, soft morning light, 35mm grain.

3. Add an output node

Add an Output node next to the prompt. From the prompt node’s right handle, drag a connection into the output node’s prompt target handle.

4. Pick a model

In the output node’s model dropdown, pick an image model. Nano Banana 2 is a good default — fast, cheap, supports text-to-image and image-to-image.

For higher quality (and more credits per generation) try Nano Banana Pro, GPT Image 2, or Imagen 4 Ultra. See Image Models for what each one is good at.

5. Generate

Click Generate on the output node. The credit cost shows next to the button before you commit.

The image appears inline as soon as it’s ready. The board auto-saves — there is no save button.

What’s next

• Connect a source image to do image-to-image editing (see the Image Node)
• Try bulk generation with wildcards (tutorial)
• Generate your first video