Google is following Tuesday’s launch of Gemini 3 Pro with Nano Banana Pro. The image generation and editing model is officially Gemini 3 Pro Image, but the viral moniker is sticking around.
The original model (Gemini 2.5 Flash Image) was announced at the end of August. Nano Banana Pro is based on Gemini 3 Pro. It uses the base model’s “state-of-the-art reasoning and real-world knowledge to visualize information better than ever before.”
Nano Banana Pro can create more accurate and legible text in images across multiple languages, with the latter made possible by Gemini 3 Pro’s enhanced multilingual reasoning. Stylistically, you can leverage a “wider variety of textures, fonts, and calligraphy.”
Prompt: Translate all the English text on the three yellow and blue cans into Korean, while keeping everything else the same
Make 8 minimalistic logos, each is an expressive word, and make letters convey a message or sound visually to express the meaning of this word in a dramatic way. composition: flat vector rendering of all logos in black on a single white background
Similarly, this model lets you adjust camera angles, change the focus, apply sophisticated color grading, and transform scene lighting, like changing from day to night or creating a bokeh effect. It also offers improved localized editing to “select, refine, and transform any part of an image.” Various aspect ratios are available along with 2K and 4K resolutions.
- 1+2 Prompt: Turn this scene into nighttime
- 3: Change lighting of this portrait to from the left, diffused and soft
- 4: Focus on the flowers
Nano Banana Pro lets you blend up to 14 images while “maintaining the consistency and resemblance of up to 5 people.”
- Combine these images into one appropriately arranged cinematic image in 16:9 format
- Combine these images into one appropriately arranged cinematic image in 16:9 format and change the dress on the mannequin to the dress in the image
- A medium shot of the 14 fluffy characters sitting squeezed together side-by-side on a worn beige fabric sofa and on the floor. They are all facing forwards, watching a vintage, wooden-boxed television set placed on a low wooden table in front of the sofa. The room is dimly lit, with warm light from a window on the left and the glow from the TV illuminating the creatures’ faces and fluffy textures. The background is a cozy, slightly cluttered living room with a braided rug, a bookshelf with old books, and rustic kitchen elements in the background. The overall atmosphere is warm, cozy, and amused.
One place where the model’s reasoning, world knowledge, and real-time information comes together is when generating infographics and diagrams.
Create an infographic that shows how to make elaichi chai
Nano Banana Pro is rolling out globally to the Gemini app today. Once you’re using the Thinking (Gemini 3 Pro) model, select “Create images.” Free users have a limited quota before returning to the original Nano Banana. Google AI Plus, Pro, and Ultra subscribers get higher usage limits.
Meanwhile, Google is dropping the watermark for AI Ultra subscribers who are often using it for professional work. It remains in place for everyone else, while Google now has a @SynthID extension in the Gemini app. This lets you upload images to check if it’s generated, with video and audio support coming soon.
The new model is also coming to AI Mode for subscribers in the US, while it’s available to paid NotebookLM users globally. Nano Banana Pro will be available in Flow with Google AI Ultra.
In Google Workspace, it’s coming to Google Slides and Google Vids.
It’s also coming to Google AI Studio, the Gemini API, Vertex, and Google Antigravity, as well as Google Ads.
FTC: We use income earning auto affiliate links. More.
