Nano Banana 2.1
is here.

Q: How can I create better images?

Start with a simple formula. Try <Create/generate an image of> <subject> <action> <scene> and then build from there. For example, "Create an image of a cat napping in a sunbeam on a windowsill." Be specific with as much detail as you can dream. Prompts should include as many specifics as you can think of, so instead of saying, "Create an image of a woman in a red dress," try "Create an image of a young woman in a red dress running through a park." The more details you provide, the better Gemini is at following your instructions. Take composition, style, and image quality into consideration. Think about how you want the elements in your image to be arranged (composition), the visual style you want to achieve (style), the desired level of image quality (image quality), and the aspect ratio (size). Try something like, “Generate an image of a blurry poky porcupine flying in space in the style of an oil painting with 2:3 aspect ratio.” Creativity is your friend. Gemini is great at creating surreal objects and unique scenes. Let your imagination run wild. If you don’t like what you see, just ask Gemini to change it. With our image editing model you can take control of your images by telling Gemini to change the background, replace an object, or add an element – all while preserving the details you love.

Q: How does Gemini approach safety?

Consistent with our AI Principles , this AI image generator was designed with responsibility in mind. And to ensure there’s a clear distinction between visuals created with Gemini and original human artwork, Gemini uses an invisible SynthID watermark, as well as a visible watermark to show they are AI-generated. Gemini's outputs are primarily determined by user prompts and like any generative AI tool, there may be instances where it generates content that some individuals find objectionable. We’ll continue to listen to your feedback through the thumbs up/down buttons and make ongoing improvements. For more details, you can read about our approach on our website .

Bring your wildest ideas to life at the speed and quality you need with Nano Banana. Available for free. Upgrade to a Google AI Plan to unlock Nano Banana 2.1, our most advanced image model with enhanced quality, reasoning, and visual design.

Try Nano Banana 2

Make yourself the main character.

Be the hero of your story with a custom AI Avatar. Upload your image once to create endless videos, collaborate with friends, and stay in control with secure sharing settings.

Dial in every detail
with Nano Banana.

Totally transform the vibe of your image. Shift from sunny day to moody night, play with camera angles to find the perfect view, and adjust the focus to make your subject pop.

Style applied in seconds.

Reimagine the look of your image. Take the texture, color, or style from any reference photo and apply it to your subject. It’s the easiest way to experiment with different aesthetics without starting from scratch.

One visual, many sizes.

Make your creations look professional everywhere you share them. Instantly resize them to fit whatever format you require – all without cropping the details you love.

Your words, placed just right.

Create logos, invites, posters, comics, and whatever else you need with clear text. Words fit right into your creation, in many languages.

Choose the right model for your needs

Nano Banana 2

Image generation and editing model

Free

Character Consistency

Text rendering

Combine photos

Precise editing

2K resolution

World knowledge

Nano Banana 2.1

Our best image generation and editing model

With a Google AI plan

Character Consistency

Maintain a character’s appearance across generated images.

Text rendering

Generate clearer, more accurate text.

Combine photos

Seamlessly blend multiple images.

Precise editing

Fine-tune lighting, camera angles, and aspect ratios.

2K resolution

Produce crisp, professional-grade images.

Enhanced World Knowledge

Create accurate, detailed infographics and diagrams.

More Images

Enjoy higher generation limits with paid plans.

Frequently asked questions

Is image generation available in my country?

AI image generation is available in all languages and countries where the Gemini app is available.

How can I find the image generation and editing model?

To access Nano Banana, select "🍌Create images" from the tools menu. Then add a prompt or upload an image to edit.
Google AI Pro, Plus, Ultra users have access to our best image model, Nano Banana 2.1, and can regenerate images using Nano Banana Pro by selecting the three dot menu and then “Redo with Pro”.

How can I create better images?

Start with a simple formula. Try <Create/generate an image of> <subject> <action> <scene> and then build from there. For example, "Create an image of a cat napping in a sunbeam on a windowsill."
Be specific with as much detail as you can dream. Prompts should include as many specifics as you can think of, so instead of saying, "Create an image of a woman in a red dress," try "Create an image of a young woman in a red dress running through a park." The more details you provide, the better Gemini is at following your instructions.
Take composition, style, and image quality into consideration. Think about how you want the elements in your image to be arranged (composition), the visual style you want to achieve (style), the desired level of image quality (image quality), and the aspect ratio (size). Try something like, “Generate an image of a blurry poky porcupine flying in space in the style of an oil painting with 2:3 aspect ratio.”
Creativity is your friend. Gemini is great at creating surreal objects and unique scenes. Let your imagination run wild.
If you don’t like what you see, just ask Gemini to change it. With our image editing model you can take control of your images by telling Gemini to change the background, replace an object, or add an element – all while preserving the details you love.

How does Gemini approach safety?

Consistent with our AI Principles, this AI image generator was designed with responsibility in mind. And to ensure there’s a clear distinction between visuals created with Gemini and original human artwork, Gemini uses an invisible SynthID watermark, as well as a visible watermark to show they are AI-generated.

Gemini's outputs are primarily determined by user prompts and like any generative AI tool, there may be instances where it generates content that some individuals find objectionable. We’ll continue to listen to your feedback through the thumbs up/down buttons and make ongoing improvements. For more details, you can read about our approach on our website.

How can I tell if an image was created with Google AI?

Simply upload an image to the Gemini app and ask if it was generated by Google AI. This verification is powered by SynthID, our digital watermarking technology. It is currently available for images, audio, and video support.

You can find out more about how we’re increasing transparency in AI content with SynthID in our blog post.