Google Gemini’s new image editor keeps characters consistent, fuses images and understands sketches

Google Gemini may not be the most popular AI chatbot, but it still has millions of users worldwide. The tech behemoth gave the Gemini app native image editing features in April of this year. Now, Google is giving Gemini’s image editing feature a significant boost.

Google revealed in a blog post that Gemini’s image editing feature is now powered by the Gemini 2.5 Flash Image large language model, which can “create and edit images using Gemini’s world knowledge, blend multiple images into a single image, maintain character consistency for rich storytelling, and make targeted transformations using natural language.”

What’s new with Gemini’s image editor?

As a result, you may now edit Gemini-generated photographs while preserving a character’s characteristics and nuances “from one image to the next.” For instance, a character or item can now be placed in various locations, have its appearance preserved between several prompts and adjustments, and display a product from various perspectives while maintaining the subject.

According to Google, its new model can also follow visual standards such as uniform employee badges, dynamic product mockups for a catalog, and real estate listing cards. In addition, Gemini 2.5 Flash Image allows for “precise local edits with natural language,” which can be used to remove stains from shirts, blur the backdrop of an image, eliminate a person, and add color to a black and white picture.

The tech giant added that the new text-to-image generation large language model also has “native world knowledge.” This means Gemini can now read and understand hand-drawn diagrams, solve real-world questions and follow complicated editing instructions all in a single step. Gemini 2.5 Flash Image can now also lets you put an object into a scene, fuse images, apply a texture or put a colour scheme in a room.