
Google DeepMind has rolled out a new upgrade to the Gemini app, bringing users a more powerful way to edit and transform images. The update introduces a model nicknamed Nano Banana, which has already gained recognition as one of the world’s top-rated image editing systems. Now integrated into Gemini, it allows for more accurate, creative, and personalized editing experiences.
Earlier this year, Gemini introduced native image editing. Since then, developers have focused on refining it—especially on maintaining likeness when editing photos of people or pets. The new model ensures subtle details remain consistent, so even when you’re trying out a retro hairstyle or dressing your dog in a tutu, the subject still looks like themselves.
With just one photo, users can now ask Gemini to apply changes ranging from backgrounds and costumes to props and environments. Edited images can even be re-uploaded to turn into short videos.

Here are a few ways you can take advantage of Gemini’s latest editing capabilities:
To ensure transparency, all AI-generated or edited images in Gemini include a visible watermark along with Google’s invisible SynthID digital watermark.
This upgraded image editing experience is live in the Gemini app starting today. Whether you’re looking to reimagine your selfies, experiment with design, or just have fun with creative edits, Gemini gives you more control than ever to bring your ideas to life.