Google updates AI model Gemini for image editing

• The updated model Gemini 2.5 Flash Image is available to all users.
• The model ensures precise editing of images based on natural queries.
• Google has imposed limitations on the creation of inappropriate content.

This is reported by TechCrunch, CNET.

Google has introduced the updated AI model Gemini 2.5 Flash Image, which provides users with more precise capabilities for editing images. This update, which received the name "nano bananas", is available to all users of the Gemini program, including developers through the Gemini API, Google AI Studio, and Vertex AI.

The new model allows for editing based on natural language queries, while maintaining the integrity of faces, animals, and other details. For example, if a user requests to change the color of a shirt in a photo, the result will be more precise than with competitors.

The Gemini model has already attracted user attention on social media, where they have rated its capabilities on the LMArena platform. Google claims that the new model is the most advanced compared to analog products.

At Google, they plan to maintain certain limitations on what users can create to avoid problems with inappropriate or inappropriate images. The company has also introduced visual indicators for AI-generated images, so users can more easily identify their origins.

The updated Gemini model also offers new functions, such as changing fonts and the ability to combine different elements in a single image. Users can, for example, combine images of people and flowers to create a new design.

Tags: Technology/AI