As expected, an AI image model known as ‘Nano Banana’ that was making a big impression last week is in fact made by Google. The tech giant announced it last night along with its actual name ‘Gemini 2.5 Flash Image.’
“This update enables you to blend multiple images into a single image, maintain character consistency for rich storytelling, make targeted transformations using natural language, and use Gemini’s world knowledge to generate and edit images,” Google writes.
The company has set up a web tool for editing photos, which I used to remove the cup from the dog photo.
Business Insider declares that today is a “bad day” for Adobe. The website says that it has been testing Gemini 2.5 Flash Image for “several days” and found it to be deft at editing photos.
Nano banana is genuinely blowing my mind.
“Add a third bag of dog food in the cart the same as the other two”
It’s disturbingly good. Photoshop might be cooked this decade forever. pic.twitter.com/vC8x0lSOmk
— Chris (@chatgpt21) August 19, 2025
🍌 Google’s new image model, nano-banana, is the best I’ve seen.
It’s the first one with good object persistence, notice how the beach wasn’t altered at all and how well it followed the prompt. pic.twitter.com/x0h29HHDVG
— Mariano Pardo (@marian2js) August 20, 2025
BI notes that its ability to complete tasks like changing the color of an item of clothing or adding details such as a person’s glasses, outperforms comparable apps.
Adobe announced that Google’s new AI model will be integrated into Adobe Firefly and Adobe Express, emphasizing that its ecosystem remains the premier hub for creators who want seamless movement and collaboration across different apps.
Gemini 2.5 Flash Image, AKA Nano Banana, can be tried via the Google AI Studio.
