Generation from text and images
In addition to generating images from text prompts, it also supports image generation based on existing images.
Google's fast and highly efficient standard image generation model. It can quickly generate photorealistic or anime-style visuals from text or existing images.
Each model has its own Playground, pricing, and field docs. Filter by capability to open the one you need.
Model id and a short note on what each capability is for.
| Model | ID | Description |
|---|---|---|
| Nano Banana(text to image) | nano-banana-text-to-image | Google's ultra-fast, lightweight image generation model that turns ideas into reality with overwhelming speed |
| Nano Banana(image to image) | nano-banana-image-to-image | Google’s ultra-fast, lightweight visual generation model, boasting overwhelming speed |
A suite of features supporting smooth generation from text and images, accommodating diverse styles and commercial use.
A simple and spacious courtyard with a snowy landscape. A woman in a quiet kimono blends in with the morning light.
Prompt
A simple Japanese Zen garden, a snowy morning, a woman in a black kimono sitting in seiza on a tatami mat, gazing at the dry landscape of the rock garden. Outside the window, snow-covered pines and distant mountains, wit…

Generated with Nano Banana

Generated with Nano Banana Pro

Generated with Nano Banana 2
The end-of-days desert, with motorcyclists racing forward, raising clouds of sand. A blood-red sunset and desolate ruins.
Prompt
The desolate desert of the apocalyptic world, a lone motorcyclist, wearing a tattered leather jacket and gas mask, riding a heavily modified heavyweight motorcycle, raising a huge cloud of dust behind him. A blood-red su…

Generated with Nano Banana

Generated with Nano Banana Pro

Generated with Nano Banana 2 Lite
A woman in a white dress, gracefully floating in the water, surrounded by enchanting light and bubbles.
Prompt
A young and beautiful woman in a white silk dress, fantastically floating in the water. The fabric of the dress gracefully spreads like it's weightless, undulating in slow motion. Her hair spreads like a halo in the wate…

Generated with Nano Banana

Generated with Nano Banana Pro

Generated with Nano Banana 2
Typical jobs this series is used for.
Instantly generate 1K resolution images from text to quickly brainstorm ideas and create rough designs during the planning stage.
It supports text rendering, allowing you to smoothly create social media banners, promotional materials, and more from text prompts.
Easily edit and transform existing reference images into a variety of styles, such as photorealistic or anime.
Supports tags for commercial use, efficiently generating image assets for business purposes such as web advertisements and article illustrations.
Check production limits and starting credit cost before you pick another model for the same job.
| Model | Multimodal reference inputs | Max resolution | Sousaku starting price |
|---|---|---|---|
| Nano Banana | ❌ | Up to 1K | 1 Credits |
| Nano Banana Pro | ❌ | Up to 4K | 2 Credits |
| Nano Banana 2 | ❌ | Up to 4K | 2 Credits |
From sign-up to your first successful call. The same steps work for every model.
Sign up and verify so you can issue an API key and use Playground.
Open a card above to see that model's details, pricing, and field docs.
Confirm inputs and parameters in the form before you automate.
The field docs on the detail page list required parameters. Use the same names in create_task.
Call the generate API with your key, poll until the task succeeds, then download the result.
Track credit use on the model's pricing page and in the dashboard.
Other series on Sousaku. One API key, one task flow.