Google’s Gemini AI Gets Major Image Editing Update: Nano Banana

Back in April, Google’s Gemini app received native image editing ability. The feature allows users to edit photos that they manually upload, as well as the ones created by AI, using conversational language. The editing functionality wasn’t perfect, as the subject’s appearance isn’t consistent throughout the edits. However, Google has now enhanced the Gemini AI chatbot’s image editing capabilities through a major update.

A new model from Google DeepMind powers the updated image editing features of the Gemini app. The firm has designed it “with particular focus on maintaining a character’s likeness from one image to the next.” Thanks to the update, you can change costumes or locations in the photos, blend two images, and make multiple, incremental edits.

Gemini’s new image editing update lets you bring your vision to life

In a blog post, Google said that the Gemini app’s new image editing features can make photos of your friends, family, and even your pets look consistently like themselves. “Whether you’re trying out a 60’s beehive haircut or putting a tutu on your chihuahua,” reads the blog post. You can now simply upload a photo of a person or a pet and give them a costume or a location change.

You can also upload multiple images and blend them together by using any text prompt. For example, you can upload your photo and another of your pet and create a portrait of you both in any scenario. The AI is now able to maintain realism for both subjects in a blended image.

Gemini now lets you make multiple, incremental edits

Gemini’s latest image editing update also allows for multiple edits. It means that you can use one prompt and then take the creation even further with another incremental text prompt. “Take an empty room, paint the walls, then add a bookshelf, some furniture or a coffee table,” reads the Google blog example. You can create new worlds from scratch or reinvent ones from real photos.

Furthermore, Google has added a new design mixing capability in the Gemini app. This allows you to take one style—perhaps anime-like—and mix it with another, such as a more real-world scenario. In Google’s example, the design of butterfly wings transforms the look of a dress.

It’s worth mentioning that the newly created images feature a watermark in the corner to indicate that an AI tool generated them. Furthermore, Gemini will tag the photos with Google’s invisible SynthID watermark.

Gemini’s new image editing features are available to both paid and unpaid users globally starting today. Officially, the new image editing features in the Gemini app are provided by Nano Banana, which is the search engine giant’s latest state-of-the-art image generation and editing model.

The post Google’s Gemini AI Gets Major Image Editing Update: Nano Banana appeared first on Android Headlines.