SupportGet started

Create images

Write a prompt, pick a model and a shape, and get a set of images back.

Last verified

Overview

The Create page is where your work begins. Describe what you want, choose a model, a shape and how many images, and press Create. A new row appears at the top of the feed, in the project you have open, and fills in as each image finishes.

Say you are illustrating a picture book about Fern, a hare in an oversized olive coat. Ask for four 3:4 images and you have four covers to choose from before your tea goes cold.

Write a prompt

Type in the prompt box at the bottom of the page. Enter sends it and Shift+Enter starts a new line.

A good first prompt names the subject, where it is, and how it should look: "A brown hare in an oversized olive coat walking along a ridge of round green hills at dawn, gouache, picture book style." The model decides anything you leave out, so name everything you care about.

Pick a model

Open the model menu from the composer. New accounts start on Nano Banana 2. The list shows names only. Point at a model to see its details beside the list: Speed, Quality, Cost per image, and whether it Supports working from your own images.

Some models have a setting of their own, shown below their details, such as Web search on Flux 3 Image or Magic Prompt on Ideogram 4.5. Not sure which to pick? Which model for what matches models to jobs, such as Ideogram 4.5 for posters and logos.

Choose the shape and size

Select the settings button in the composer, next to the model. It shows your current choice, such as 1:1 · 1K · ×4.

  • Aspect ratio sets the shape. Pick Portrait, Square or Landscape, then use the slider for an exact ratio, from 9:16 to 21:9. A model only offers the ratios it can make.
  • Resolution sets the size, on models that offer more than one. A few models call it Quality instead.
  • Images per prompt is how many images one press of Create makes: 1, 2, 4, 6 or 8.

Get more range

Images from one prompt on one model often look alike. For more range, turn on Vary prompts or use a variety pack. With either one on, the button changes to Batch Create and shows how many images it will make.

Vary prompts, at the bottom of the image settings, writes a different version of your prompt for each image. The first image keeps your prompt exactly as you wrote it. Turn it on when the prompt is right but the results look alike. Start with Auto; Customize lets you pick what changes, such as Style or Mood, and a Direction every version follows.

A variety pack runs your prompt on up to four models at once. In the model menu, select the + next to a model to add it to the one you have. Double-click a row to go back to a single model. Each model makes Images per prompt images, so four models at 2 each is 8. To find the right model for a job, set Images per prompt to 1 and compare one image from each.

One press makes up to 48 images, and each is priced like any other image from its model.

What it costs

Each model has a price per image, shown as Cost in its details in the model menu. Higher resolutions and quality levels cost more on most models: Nano Banana 2 is 16 credits at 1K and 40 at 4K. Four images cost four times one. When a set is done, open any of its images to see what the whole set cost. Every model's price is listed in Credit costs.

If you run out, the composer says so and offers Add credits.

Set your starting point

New prompts start with your default model, aspect ratio and images per prompt. Change them in the composer and the new choice becomes the default. You can also set them in Settings > Preferences, under Composer.

Tips

  • Find the idea on Nano Banana 2 Lite, at 8 credits an image. Once you know what you want, run the prompt again on Nano Banana 2 at 2K or 4K, or on Nano Banana Pro when the image needs fine detail or text.
  • Choose the aspect ratio before you fuss over wording. A model composes for the frame you give it, so a 9:16 phone wallpaper and a 21:9 banner from the same prompt are different pictures.
  • Start with four images, the default. One image shows a single result; four show what the model tends to do with your prompt.
  • When a result is close, change one thing in the prompt at a time. Then you know what made the difference.