Nano Banana 2

Nano Banana 2

Nano Banana 2 is Google's fast, high-fidelity Gemini image model for new image generation and context-aware natural-language editing. Its strengths include instruction following, readable typography, multi-element composition, and preserving visual structure while making targeted changes.

MachGen supports text-to-image and editing with up to 14 ordered input images at 1K, 2K, or 4K across 16:9, 21:9, 3:2, 4:3, 1:1, 3:4, 2:3, and 9:16.

Why choose Nano Banana 2

Key strengths

• A balanced Gemini image model combining speed, strong instruction following, world knowledge, and high-resolution output.
• Reliable text rendering and layout awareness for posters, menus, diagrams, and marketing assets.
• Natural-language editing can preserve an existing structure while changing selected details.

Good fit for

• High-volume visual ideation, social assets, posters, diagrams, and product concepts.
• Targeted edits to backgrounds, objects, styling, or copy.
• General-purpose image work that needs a balance of quality, speed, and cost.

Inputs and output settings

This table reflects the model routes and controls currently exposed by MachGen.

Using Nano Banana 2

1. Choose a supported generation mode in Playground.
2. Add the required prompt and source or reference assets.
3. Select output settings from the controls shown for that mode.
4. Generate, then inspect the returned asset before reusing the settings through the API.

Practical guidance

• Describe the subject, action or composition, environment, and visual direction in a clear order.
• For image editing, state what should change and what should remain unchanged.

Modes available on MachGen

Text to image

Create a new still from a natural-language description of the subject, composition, lighting, style, and any text that should appear in frame.

Image editing

Attach up to 14 ordered images and describe the requested revision, including which elements should change and which should remain intact.

Output controls

Select 1K, 2K, or 4K output and one of the eight aspect ratios exposed in Playground, including 21:9.

Prompting notes

• For new images, order the brief as subject, composition, lighting, style, then exact on-image text.
• For edits, describe the delta clearly and state what must stay unchanged.
• Put exact copy in quotation marks and specify where it belongs in the layout.
• Choose the output aspect ratio in Playground instead of relying on the prompt alone.

How to get better Nano Banana 2 results

• Write exact on-image copy in quotation marks and specify its location, hierarchy, and type style.
• For edits, describe the requested change and separately state what must stay unchanged.
• Use layout language such as top-left label, centered hero, or three-column grid when structure matters.
• Review text and small factual details at full resolution before delivery.

Limits and availability

• MachGen admits only the modes and settings listed above for this catalog model.
• Source assets must finish uploading before a request can be submitted.
• Generated results can vary between requests, including when the same prompt and settings are reused.
• Nano Banana 2 is pass-through. MachGen sends the request through its upstream provider integration and returns the generated asset.

Learn more

For model background, technical details, and architecture, see the official Gemini image generation guide.

Try this model in the MachGen Playground.

Official documentation may describe capabilities or parameters that are not currently exposed by MachGen. Use the Inputs and output settings section above as the source of truth for this page.

Nano Banana 2 pricing

See Pricing for currently published MachGen rates. When available, the Playground estimate reflects the selected task and output settings.

Nano Banana 2 on MachGen

Deployment: Pass-through. Nano Banana 2 is pass-through. MachGen sends the request through its upstream provider integration and returns the generated asset.

The Playground and API sections on this page list the inputs and output settings exposed for this model.