Mysterious Nano-Banana AI Image Generator Goes Viral - Here Are 10 Wild Examples

By Chris Smith
person working on computer with virtual windows floating in air GamePixel/Shutterstock

Generative artificial intelligence enthusiasts are always on the lookout for brand-new AI models released for public testing ahead of their commercial launch, and in the past few weeks, they have discovered a mysterious "Nano-Banana" AI image generator that can create incredible results from text prompts. While it's unclear what company is behind Nano-Banana, some people think this is a Google model that the company is quietly testing in public before announcing the AI image-generation tool officially.

Since ChatGPT went viral in late 2022, we've witnessed a growing number of AI startups develop image and video generation tools. These generative AI products have seen massive upgrades this past year. ChatGPT received a built-in tool called GPT-4o image generation in the first half of the year and that model went viral almost immediately, with users creating convincing deepfakes and plenty of Studio Ghibli-style images. ChatGPT can also edit user-submitted photos in addition to generating images that look just like real photos.

Gemini gained similar image generation and editing powers, but Google's tool didn't witness a similar surge in user interest. On the other hand, Google's Veo 3 video generator saw plenty of excitement from users since Google released the model at I/O 2025. Products from lesser-known firms have also gone viral lately, like Higgsfield and its Soul AI image and video generation products.

Is Google behind Nano-Banana?

A close-up of the Gemini app. PJ McDonnell/Shutterstock

Google has not announced any updates for its image and video generation recently, but its Imagen 4 and Veo 3 products have already been turning heads this year. It's clear from Google's announcements in the past few years that using AI for generating and editing images and video is a key priority for the company.

Earlier this week, Google unveiled the Pixel 10 series, which will support new AI capabilities, including a Camera Coach tool where Gemini gives you tips on how to take better photos, and conversational language image editing support in Google Photos. The latter is particularly interesting, as it lets anyone edit their photos by using natural language to describe the changes they want the AI to make.

Could Nano-Banana be the work of Google's AI teams? According to CreativeBloq, some internet sleuths have found cryptic tweets from Googlers involved in AI development that indicate Nano-Banana is a Google product. Google AI Studio head Logan Kilpatrick posted a banana emoji on X and Google DeepMind manager Naina Raisinghani shared an image of a banana taped to a wall.

10 wild examples of Nano-Banana AI images

A concept image of working with AI tools on a computer. tadamichi/Shutterstock

The only way to use Nano-Banana right now is to go to LMArena and choose to test two anonymous AI imaging models at the same time to see which one produces the best results. LMArena is a benchmarking site for AI, and a great way for companies to hide their frontier AI models from the public, while also allowing the public to test them. Nano-Banana might show up in those tests, and the growing list of incredible Nano-Banana samples that have been posted on X show what this mysterious AI image generator can do.

Nano-Banana seems to excel at performing the kind of image edits users ask for in prompts while maintaining the quality of the original photo. Nano-Banana is also very good at moving objects in a generated picture, whether it's a person or a product. As you'll see in the samples below, the AI can turn a person's head towards the viewer with incredible ease. It can also add and replace objects, like clothes and accessories, and it can replicate objects in the photos.

The resulting images also maintain lighting conditions and perspective. More importantly, the Nano-Banana creations look like real photos, as you'll see in the following examples that were shared on X.

Replicating real objects:

Inserting faces in a photo:

Recreating ad styles:

Creating a picture using distinct photos of people:

Turning a person's face towards the camera:

Replacing objects in photos:

More object replacements:

Replacing clothes:

Creating b-roll images:

Replacing brands in photos:

Recommended