Image editing in Gemini just got a major upgrade

Google DeepMind Blog Products

Summary

Google DeepMind has released an upgraded image editing model for the Gemini app that maintains consistent likeness when editing photos of people and pets. The new model, called Nano Banana, is top-rated and enables features like outfit changes, photo blending, and style transfer while preserving character consistency.

Transform images in amazing new ways with updated native image editing in the Gemini app.
Original Article
View Cached Full Text

Cached at: 04/20/26, 08:35 AM

# Image editing in Gemini just got a major upgrade Source: https://blog.google/products-and-platforms/products/gemini/updated-image-editing-model/ Transform images in amazing new ways with updated native image editing in the Gemini app. imageNicole Brichtova Gemini Image Product Lead, Google DeepMind ## General summary The Gemini app now has a new image editing model from Google DeepMind. This update focuses on maintaining a consistent likeness when editing photos of people and pets. You can now change outfits, blend photos, and apply styles from one image to another, so try the updated image editing in the Gemini app today. Summaries were generated by Google AI. Generative AI is experimental. Text saying 'Reimagine your photos with a prompt' surrounded by a collage of AI-generated images, including a blonde woman in a bullfighting costume and a pair of pink rain boots. There are also prompt text boxes and the Gemini logo. Gemini image editing Nano Banana is the latest upgrade to image generation in the Gemini app. Try it (https://gemini.google/overview/image-generation/?utm_source=keywordblog&utm_medium=referral) Today in the Gemini app (http://gemini.google.com/), we're unveiling a new image editing model from Google DeepMind. People have been going *bananas* over it already in early previews — it's the top-rated (https://lmarena.ai/leaderboard/image-edit) image editing model in the world. Now, we're excited to share that it's integrated into the Gemini app so you have more control than ever to create the perfect picture. ## Maintain your look as you edit We launched native image editing (http://blog.google/products/gemini/image-editing) in the Gemini app earlier this year, and we've been working hard to improve it, with particular focus on maintaining a character's likeness from one image to the next. We know that when editing pictures of yourself or people you know well, subtle details matter — a depiction that's "close but not quite the same" doesn't feel right. That's why our latest update is designed to 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. Just give Gemini a photo to work with, and tell it what you'd like to change to add your unique touch. Gemini lets you combine photos to put yourself in a picture with your pet, change the background of a room to preview new wallpaper or place yourself anywhere in the world you can imagine — all while keeping you, you. Once you're done, you can even upload your edited image back into Gemini to turn your new photo into a fun video. ## Bring your vision to life with advanced editing Here are a few things to try as you explore this new image editing capability: - **Give yourself a costume or location change**: Upload a photo of a person or pet, and our model will keep their look the same in every image as you place them in new scenarios. Try putting yourself in different outfits or professions, or even see how you'd appear in another decade — all while still looking like you. - **Blend photos together**: You can now upload multiple photos and blend them together for a brand-new scene. For example, take your photo and another of your dog to create a perfect portrait of you both on the basketball court. - **Try multi-turn editing**: You can keep editing the images Gemini makes — take an empty room, paint the walls, then add a bookshelf, some furniture or a coffee table. Gemini's working with you all along to alter specific parts of an image while preserving the rest. - **Mix up designs**: Apply the style of one image to an object in another. You can take the color and texture of flower petals and apply it to a pair of rain boots, or design a dress using the pattern from a butterfly's wings. You can try this updated image editing capability in the Gemini app starting today. All images created or edited in the Gemini app include a visible watermark, as well as our invisible SynthID digital watermark, to clearly show they are AI-generated. Gemini image editing Nano Banana is the latest upgrade to image generation in the Gemini app. Try it (https://gemini.google/overview/image-generation/?utm_source=keywordblog&utm_medium=referral) ### Related stories

Similar Articles

Build with Nano Banana Pro, our Gemini 3 Pro Image model

Google DeepMind Blog

Google DeepMind releases Gemini 3 Pro Image (also referred to as Nano Banana Pro), a high-fidelity image generation and editing model with advanced controls for developers via the Gemini API and Google AI Studio.

Introducing Nano Banana Pro

Google DeepMind Blog

Google DeepMind introduces Nano Banana Pro, a new state-of-the-art image generation and editing model built on Gemini 3 Pro. The model offers improved text rendering, enhanced world knowledge integration, and high-fidelity visual capabilities available across Google products.

Google Pics is a new app that tries to fix AI image editing

The Verge

Google launches Pics, a new AI image generation app for Workspace that allows users to click on elements and leave notes to modify images, powered by Gemini and Nano Banana 2 models. It aims to simplify iterative AI image editing.

Introducing Gemini 2.0: our new AI model for the agentic era

Google DeepMind Blog

Google DeepMind introduces Gemini 2.0, a new agentic AI model with native image and audio output, enhanced tool use, and multimodal capabilities designed for the next era of AI agents. Gemini 2.0 Flash is now available to developers with wider availability planned for early 2025.