Create and edit ad-ready images with precise text, strong character consistency, and resolutions up to 4K.
Upload up to 14 reference images (PNG, JPG, or WebP).
2K and 4K add sharper small text and larger output; the price is per generated image.
Each generated image is billed separately.
Sign in to spend tokens
Prompt is required
Your generated images will appear here
Nano Banana 2.1 creates and edits ad-ready images with precise in-image text, strong character consistency, and output up to 4K. Upload up to 14 references, pick any of 15 aspect ratios, and generate one to four images per run.
Nano Banana 2.1 is a premium image model for product hero shots, social ads, lifestyle scenes, and design concepts. It turns a written brief into a finished visual and can edit existing images when you attach references.
The model is especially strong at three things ad creative depends on: small text that stays readable, a face or character that stays consistent across variations, and flexible framing from square feed posts to tall Stories and wide panoramic placements.
The workflow stays simple. Write the prompt, optionally add up to 14 reference images, choose an aspect ratio and a resolution, then generate. Every result lands in your asset library, ready to download or reuse in the rest of AI Studio.
Create premium product shots with readable packaging text and controlled studio lighting.
Place a consistent creator in branded environments for feed, Stories, and short-form ads.
Build posters and ad frames where the headline is part of the generated image, not an overlay.
Adapt one concept to square, vertical, landscape, and panoramic placements in a single session.
Swap a product or change a scene while preserving the person, layout, and visual direction from your references.
Render headlines, packaging copy, labels, and short callouts with clean spelling and stable placement.
Keep the same person or mascot recognizable across a batch of variations and multiple ad formats.
Combine a product, a person, and an art direction in one prompt, or edit an existing visual with controlled changes.
Draft at 1K, then move to 2K or 4K for sharper small text and final campaign assets.
Choose from square, portrait, landscape, vertical, and panoramic frames, plus Auto for prompt-led framing.
Generate one to four images per run and compare directions without rebuilding the setup.
Write the subject, composition, lighting, materials, and every word of text you want to appear in the image.
Optionally upload up to 14 JPG, PNG, or WebP references. Number them in the prompt so each image has a clear role.
Choose an aspect ratio for the placement, from 1:1 and 4:5 to 9:16, 16:9, and panoramic frames.
Pick 1K for drafts, 2K for sharper detail, or 4K for final hero assets.
Choose the number of images and generate. Each result is billed separately.
Download the finished images from your asset library and reuse them in other AI Studio tools.
Generate fast drafts and everyday social assets at 9 tokens for each output image.
Choose sharper detail for campaign assets at 13 tokens for each output image.
Render final hero visuals with the highest detail at 28 tokens for each output image.
If a run cannot be completed, the tokens charged for that run are returned automatically.
You can attach up to 14 references in JPG, PNG, or WebP format. Number them in the prompt so each image has a clear role.
Choose 1K, 2K, or 4K. Higher resolutions add detail for small text and large placements and are priced per generated image.
Each image costs 9 tokens at 1K, 13 tokens at 2K, or 28 tokens at 4K. A batch is priced per output image, and the total is shown before you generate.
Fifteen options are available: 1:1, 2:3, 3:2, 1:4, 4:1, 3:4, 4:3, 4:5, 5:4, 1:8, 8:1, 9:16, 16:9, 21:9, and Auto.
Yes. Generate one to four images per run. Each generated image is billed separately.
The run moves to a clear failed state and its token charge is refunded automatically. Internal technical details are never shown in the workspace.
Published 2026-11-03 · Last updated 2026-11-03