Gemini is best at modifying your photographs with a brand new mannequin replace from Google DeepMind.
The mannequin, which rose to the highest of the LMArena leaderboard below the alias “nano banana,” is definitely known as Gemini 2.5 Flash Picture. The Google DeepMind workforce says this mannequin has been educated to make topics extra constant throughout numerous edits of AI-generated photographs. This has been a difficulty for AI picture fashions, given their unpredictable nature.
The power to add and natively edit pictures in Gemini has been round since April of this yr. As a substitute of studying the technical ins and outs of picture modifying software program like Photoshop, customers can add a picture to Gemini and describe the modifications they need in easy phrases, no jargon required. With Gemini’s up to date mannequin, Google says you are able to do issues like change a topic’s outfit and site, whereas maintaining their likeness the identical.
Mashable Gentle Velocity
You can too add a number of pictures and have the topics seem collectively in the identical picture, or add and alter particular particulars in an uploaded picture to, say, see what a room seems to be like with a unique colour of paint or totally different furnishings.
This is Gemini’s try at modifying my canine into the downward canine pose and relocating her to a yoga studio. Her likeness is identical, and it efficiently edited the picture to make her eyes open, however her physique is not arched in the way in which it ought to be. (I’d know, I’ve seen this playful pose from her many instances.)
This is my canine Lola, not doing yoga
Credit score: Mashable

This is the Gemini-edited model once I prompted it to open her eyes, put her within the downward canine pose, and alter the background to a yoga studio. It is shut, however not fairly proper.
Credit score: Mashable
As Google DeepMind stated in its announcement, the mannequin may not at all times get it proper. There may nonetheless be inaccuracies with nice particulars, textual content within the picture, and inconsistencies. With my experiment, my canine’s fur seems to be overly clean, however her general coloring, measurement, and form keep the identical. All photographs have a visual watermark and an invisible watermark known as SynthID to mitigate any confusion over whether or not they’re actual or AI-generated. This replace is now dwell, so you may strive it out for your self within the Gemini app.
Matters
Synthetic Intelligence
Google Gemini