If there’s one thing you just can’t avoid in 2025, it’s artificial intelligence – better known as AI. It’s everywhere right now. Google’s Gemini is popping up in more places than ever, and it keeps getting smarter, offering tools for text, image, and even video creation.
Earlier this year, Gemini added built-in image editing, but now Google’s DeepMind has stepped things up again with a brand-new image editing suite, rolled right into the Gemini app. The best part? It’s available worldwide, and both free and paid users can try it.
The main highlight of this update is, as Google’s official blog explains, to bring “particular focus on maintaining a character’s likeness from one image to the next.” But that’s not all. Here’s a quick rundown of what Gemini can do now:
Change Outfits or Backgrounds
You can upload a photo of yourself (or someone else) and ask Gemini to change the outfit or switch up the background. The examples Google shared show how a simple headshot can turn into a doctor, baker, or even a sculptor. Basically, the possibilities are endless.
Blend Two Images Into One
This might be the most exciting new feature: combining two completely different images into one seamless picture.
In the demo, Gemini took a photo of a woman holding a basketball and another of a dog with its head out of a car window. The result? A brand-new image that looked surprisingly realistic, as if it were a real moment captured on camera. Pretty wild.
Edit in Steps, One Change at a Time
The update also supports iterative edits, meaning you can keep tweaking an image one step at a time.
As the Google blog puts it: “Take an empty room, paint the walls, then add a bookshelf, some furniture or a coffee table.”
So whether you want to redesign a space, build something from scratch, or reimagine an existing photo, you can keep layering changes until it’s exactly how you like it.
Mix Different Styles Together
Another cool upgrade is in “design mixing.” This lets you blend different visual styles together. For instance, you could take something cartoon-like and merge it with a more realistic or artistic vibe.
One example came from the prompt: “turn this into a stunning dress.” Gemini didn’t even need to be told what the original image was – it simply transformed it into something stylish and impressive.
The Bottom Line
Google Gemini just got a serious upgrade in the world of image creation.
It’s exciting stuff, but also a little bit unsettling as the line between real and AI-generated images keeps getting blurrier. To help with that, Google uses an invisible SynthID watermark so you’ll know when an image was made by AI. Whether people will actually check for that is another question.
ALSO READ: Google Confirms Global Rollout of Developer ID Checks to Protect Android Users
