Nano Banana 2.1 is Google’s latest image generation model — the fast, high-efficiency counterpart to Nano Banana Pro. It builds on Nano Banana 2 with sharper output, better text rendering, and real-time grounding, while keeping the speed and low cost of the Flash family.
What it can do
Generate images from text. Describe what you want and the model creates it — photorealistic scenes, illustrations, product mockups, infographics, whatever you need.
Render text accurately. Text in images is crisp and readable, with support for multiple languages — signage, posters, labels, and infographics come out clean.
Edit existing images. Pass in one or more images along with a text prompt to transform them — change backgrounds, swap colors, adjust styles, or combine several images into one scene. You can use up to 14 reference images at once.
Ground in real-world information. Turn on google_search to generate images based on real-time information like weather, sports scores, or recent events. Turn on image_search to pull web images as visual context for generation.
Resolutions and aspect ratios
Output at 1K, 2K, or 4K. Higher resolutions take longer to generate.
Supports a wide set of aspect ratios including 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, and the ultra-wide and ultra-tall 4:1, 1:4, 8:1, and 1:8. Set match_input_image to automatically match the aspect ratio of your input image.
Output format
Choose between jpg (default) and png.
Links
You can try Nano Banana 2.1 on the Replicate playground.