Your first image
Let's make one image end to end. This takes about a minute and costs roughly $0.03 on Gemini's cheapest image model.
The fastest path: the starter graph
The setup wizard offers a starter graph on its last step, right after it has you create your first project — a ready-wired Prompt → Refine → Text→Image → Preview chain on Nano Banana 2 Lite. Click Add starter graph, then hit ▶ Run in the toolbar. Done. (Re-open the wizard any time from File ▾ → Setup wizard….)
Build it by hand
- Add a Prompt node. Press
Tabover the canvas (or + Node) and pick Prompt. Type a description:A sunlit modern villa at golden hour, floor-to-ceiling glass, a calm reflecting pool, photographic
- Add a Text→Image node. Drag from the Prompt node's output onto empty canvas — the add menu opens filtered to compatible nodes; pick Text → Image. It wires up automatically. In the node, choose provider Gemini and model Nano Banana 2 Lite.
- Add a Preview node the same way, wired from the Text→Image output.
- Run. Click ▶ Run (or the ▶ on the Text→Image node to run just it). ▶ Run never generates blindly: it first replays everything that is already cached (free), then asks once, with the estimate, before anything is generated. On a fresh graph that is one dialog: Generate calls Gemini with your key, downloads the image to your project's outputs folder, and shows it inline. The node badge reports the cost.
What just happened
- Brut made one call to Gemini on your key and saved the image in your project's outputs folder.
- The node remembered the result together with what produced it. Run again and it's free — nothing changed, so nothing is re-billed. Change the prompt and only that node re-pays. See Never pay twice.
- The generation was recorded in your project ledger — click the 🕘 on the node to see its history and re-pin any past result.
429 RESOURCE_EXHAUSTEDon the first call → your Gemini key isn't billing-enabled (the free tier has zero image quota). Enable billing in Google AI Studio. See Google Gemini.- A ⚠ "Add your … key" button on the node → that provider isn't configured; click it to jump to the wizard.
- An image edit comes back with no image (the error mentions
OTHER) → Gemini refused it without saying why, usually because of an input image (a real person's name in facade lettering, a face, a logo) rather than the prompt. Remove or crop the offending image.
Next
- Refine your prompts with the Prompt Helper.
- Image generation — editing, inpainting, composing.
- Multi-Shot — a contact sheet of viewpoints from one scene.