Google released Gemini 2.5 Flash Image (code-named Nano Bananas) on the Gemini mobile app, enabling voice- and text-based image generation and edits. The engine can swap participants in photos, change clothing, merge people from real images with new backgrounds, and synthesize missing limbs and clothing details. The web version does not yet support all features. Demonstrations show Gemini placing a torso-only photo into a chair, drawing arms and legs, completing a half-visible t-shirt logo, and changing pants color on command. The tool can remove objects from photos and extend surrounding shadows to preserve realism.
"Just give Gemini a photo to work with, and tell it what you'd like to change to add your unique touch. Gemini lets you combine photos to put yourself in a picture with your pet, change the background of a room to preview new wallpaper or place yourself anywhere in the world you can imagine - all while keeping you, you," the Chocolate Factory said.
When he uploaded both photos to Gemini on his phone, he asked the engine to draw him seated in the red chair. Gemini not only placed Piltch in the red chair, but drew arms and legs for him that weren't in the original torso picture. It even completed the logo on his t-shirt that was only half visible in the original image.
Collection
[
|
...
]