Nano Banana 2.1 | Edit.

Nano Banana 2.1 Edit Overview

Google Nano Banana 2.1 Edit transforms reference images with text instructions. Revise visual concepts with supported resolutions for design and content teams.

The model revises supplied image references from a text instruction with selectable image-delivery settings.

Nano Banana 2.1 Edit from Google is available through each::labs in the nano-banana-2.1 family. Required fields are prompt, image_urls.

aspect_ratio: Auto keeps the input image's aspect ratio; explicit ratios are sent unchanged. resolution: Resolution.

Use the Nano Banana 2.1 Edit API when you need this transformation or analysis as a repeatable step in an application or creative pipeline. The sections below distinguish the required material, adjustable controls and checks that matter before delivery.

Capabilities

• The model revises supplied image references from a text instruction with selectable image-delivery settings.
• aspect_ratio: Auto keeps the input image's aspect ratio; explicit ratios are sent unchanged.
• resolution: Resolution.
• num_images: Number of images to generate.
• image_urls: Images to edit or use as references.

Use Cases for Nano Banana 2.1 Edit

Nano Banana 2.1 Edit is useful when this specific operation fits between source preparation and delivery. These scenarios show how it can support different parts of a working pipeline.

Creators

Revise a product image. Use a representative source or a concise brief, then inspect the result before preparing a larger set of assets.

Design and marketing teams

Combine a creative reference with a new scene. Compare the result with the intended message, composition and destination. Keep reviewable versions of the source and output.

Developers

Explore a campaign variation. Inspect the actual returned value before connecting it to another step, and keep the chosen request settings with the result.

Start with a clear definition of the desired result and use the exposed controls to reach it. Keep any additional generation, editing or application logic in separate steps so that the effect of this operation remains easy to review.

Tips and Tricks

Make the main subject, composition, lighting and intended visual style unambiguous. When references are available, state which details should be retained and which should change. Start with one clear creative direction before adding several competing requests.

• resolution: Resolution.
• num_images: Number of images to generate.

• Example direction: “Replace the background with a softly lit studio; keep the subject, colors and framing unchanged.”
• Example direction: “Make the lighting warmer while preserving the main subject and its visible details.”

Compare one deliberate adjustment at a time. Inspect the part of the result affected by that change, then check the rest of the asset or response for unwanted side effects before reusing the settings.

Technical Specifications

• Result type: array.
• Required fields: prompt, image_urls.
• aspect_ratio: string; options 1:1, 3:2, 2:3, 3:4, 1:4, 4:1, 4:3, 4:5, 5:4, 1:8, 8:1, 9:16, 16:9, 21:9, Auto.
• resolution: string; options 1K, 2K, 4K.
• output_format: string or null; options png, jpeg, webp, None; default "png".
• prompt: string.

image_urls: Images to edit or use as references.

Values must use the types and accepted options listed in the parameter reference. A displayed default does not remove a required-field requirement. Choose a supported output setting for this entry rather than borrowing a preset from a related model.

Things to Be Aware Of

Review lettering, small structures, edges and any requested product details at the intended display size. An attractive first impression is not enough to establish that a visual matches its brief.

Optional settings are not necessarily interchangeable with those on another entry in the same family. Use the accepted names, types and values shown for this operation.

For media-based inputs, supply a directly retrievable file URL rather than a page containing the asset. Keep the source available while processing. Check the final content in the destination player, editor or application, not only the request status.

Key Considerations

Describe preserved details alongside the edit, and check text, identity and boundaries in the result.

Google Nano Banana 2.1 Image Edit Standard Global token rates (input $1.50/M, cached $0.15/M, text+thinking $7.50/M, image output $30/M); actual usage only. No discount applied.

Prepare prompt, image_urls before starting. Optional settings include aspect_ratio, resolution, num_images. Keep these settings aligned with the intended delivery, especially when a later step expects a particular type or format.

Run a representative request before scaling to a larger collection. Judge the result against the source and the brief, and account for all generated outputs or usage-sensitive options when estimating a batch.

Limitations

• image_urls: minimum items: 1; maximum items: 14; item string; item format: uri.
• aspect_ratio: allowed values: ["1:1", "3:2", "2:3", "3:4", "1:4", "4:1", "4:3", "4:5", "5:4", "1:8", "8:1", "9:16", "16:9", "21:9", "Auto"].

Unsupported parameters do not establish additional capabilities. A generated result can differ from the intended brief, so review detail and consistency before publication.