Follow ZDNET: Add us as a preferred source on Google.
ZDNET’s key takeaways
A mystery ‘nano banana’ image editing model climbed the charts.
DeepMind was secretly behind the model, which is now available. Users can get started for free in the Gemini app.
Every now and then, the LMArena will have a mystery model with a fun name shoot up to the top of the leaderboard. Shall I remind you of OpenAI’s Project Strawberry? More recently, a mystery ‘nano banana’ model climbed to the top of the LMArena’s photo-editing models on early previews (where it still resides), earning the title of ‘top-rated image editing model in the world,’ and you can now access.
Also: You can now add AI images directly into LibreOffice documents – here’s how
On Tuesday, Google DeepMind revealed that it was responsible for the high-performing photo editing ‘nano banana’ model. With the model, users can edit pictures using natural language prompts while keeping the essence of the image intact better than ever before, and it is being integrated right in the Gemini app.
What can you do with the model?
If you have ever uploaded an image of yourself into an AI image generator and asked it to create a new version of it in some way, for example, making it a watercolor version of yourself or anime, you may have noticed that your features sometimes don’t get lost in translation. This new model aims to change that, making the subject, whether it is a pet or a person, look like themselves.
Google suggests putting photo editing to the test by changing your clothing or giving yourself a costume, or even changing your location entirely. As seen in the GIF below, the edited version keeps the person’s appearance the same amidst outfit changes. These edits are more entertaining, but the AI editing tool can also be used for more practical edits.
For example, you can take elements of two different photos and blend them together to create a new one. Google shares an example of a solo shot of a woman being combined with a short solo shot of a dog to make it look like they are cuddling. In a way, it is like everyone gets access to the Add Me feature that Google has been offering on its Pixel phones.
Also: How a Meta partnership with Midjourney could inject more AI into future products
With the model, you can also take advantage of multi-turn edits, in which you keep using prompts to tweak an element of the same photo until you get the intended result, such as adding different pieces of furniture to a room or adding different elements to the background of your photo. You can also take elements of one photo, such as a color, and apply them to a new image.
How can you try it?
The updated image editing is already available in the Gemini app. All you need to do is enter your prompt to get started. Like all Gemini-generated images, images created or edited with this updated model will have the SynthID digital watermark, delineating that they are AI-modified.