Google's Image Editing Model Is Making a splash ahead of its official Tuesday launch

Google's image editing prototype is causing a stir

 

Google's Image Editing Model Is Making a splash ahead of its official Tuesday launch

Google has updated its Gemini chatbot with a new AI image model that gives users finer control over image editing. This move aims to keep up with OpenAI's popular image creation tools and attract users from rival ChatGPT.

The update, called "Gemini 2.5 Flash Image," will begin rolling out Tuesday to all Gemini app users, as well as developers via the Gemini API, Google AI Studio, and Vertex AI platforms. The new image model in Gemini is designed to make more precise image edits based on user requests in natural language, while preserving the consistency of faces, animals, and other details, something most competing tools struggle with, according to a report by TechCrunch, a technology news website, reviewed by Al Arabiya Business.

For example, when you ask ChatGPT or xAI's Grok to change the color of someone's shirt in a photo, the result might include a distorted face or unwanted background changes. But Google's new tool has already attracted attention even before its official unveiling. In recent weeks, social media users have praised an impressive AI-powered photo editor on the crowd-sourced AI model evaluation platform LMArena.

The model appeared anonymously to users on the platform under the pseudonym "Nano Banana." Google confirmed on Tuesday that the Nano Banana model that has become popular in recent days is the Gemini 2.5 Flash Image model, according to Axios.

Currently, free Gemini users can make up to 100 photo edits per day, while paid users can make ten times that number using the new AI model. Under the nickname "Nano Banana," the model outperformed other models on the LMArena photo editing platform and created a buzz on social media.