Google wants you to ditch Photoshop for Gemini. A new generative AI model, Gemini 2.5 Flash Image, upgrades Gemini's ability to edit your photos natively in the Gemini app. It's available now for all Gemini users, free and paying, and is rolling out in preview this week in the Gemini API and Google AI Studio and Vertex AI.
A recent preview version of the new model on LMArena sparked interest from Gemini fans, even though the model only ranked seventh as of Monday, behind leaders like OpenAI's image model and Flux's Kontext Pro and Max. It's been referred to as the "nano bananas" model by AI enthusiasts, spurred on by a recent X post from Josh Woodward, Google's vice president of Google Labs and Google Gemini.
You don't need to do anything to access the new model; it's automatically added to the base Gemini 2.5 Flash model. All you have to do is upload an image and type out your prompt, and Gemini will attempt to edit it. You should notice a difference when you ask Gemini to edit photos -- more precise edits and fewer errors from hallucinations. Adobe Express and Firefly users can also access the new model now.
Some new features include the ability to replace backgrounds and layer multiple edits. You can also combine different elements with "design remix." For example, you can upload an image of a pair of rain boots and a pink rose, and Gemini will reimagine the rain boots in a floral pattern echoing the pink rose. You can also blend two photos together, creating a kind of composite image.
This is one example of how Gemini's design mixing tool could work. Google/Screenshot by CNET
Google's Gemini privacy policy says it can use the information you upload for improving its AI products, which is why the company recommends avoiding uploading sensitive or private information. The company's AI prohibitive use policy also outlaws the creation of illegal or abusive material.
Google has been investing heavily in its generative media models this year, dropping updated versions of its image and video generator models at its annual I/O developers conference. Google's AI video generator Veo 3 stunned with synchronized audio, a first among the bevy of AI giants. Creators have made more than 100 million AI videos with Google's AI filmmaker tool, Flow. NotebookLM, an experimental product from Google Labs, also took off in popularity with its ability to turn any set of documents into a personalized podcast.
For more, check out the best AI image generators and everything announced at last week's Made by Google Pixel 10 event.