- Google’s Gemini can now edit both AI-Generated and Personal Photos using Text Records
- The editing tools allow for precision changes using AI
- Gemini now also supports uploading up to 10 images or files at once
Google’s Gemini AI takes a canvas and palette for your AI-driven image creation in a few major upgrades. Gemini can now edit images directly within its chat interface and you can send a lot of images (or other files) for it to investigate at the same time.
The new editor can work AI -Magi in any image you upload or that Gemini produces. You simply ask Gemini to make the changes you want. You can change the background of your holiday image to put your sad Airbnb kitchen on a Santorini cut, get rid of the mustard pair on your jacket and even put a fun hat on your dog despite her rejection of all headgear in real life.
You can apply more edits through your conversation with Gemini and stack changes as you go. And each change holds previous changes, so you don’t have to start from scratch when you decide that the last few edits made things worse.
Under the cap, Gemini’s editor runs a combination of tools that work together so you don’t end up with a visual Frankenstein’s monster, sewing together conflicting structures, lighting, angles and other aspects of the image. Gemini promises to keep things grounded in reality, even when your imagination goes out of the rails.
Google claims that the editor will have many positive uses for a number of professions. Teachers could quickly build illustrated storyboards, designers could make a portfolio of product images, and architects may be able to visualize adjustments to build design in the middle of meetings.
The editor pairs nicely with Google’s move to blow up the upload boundary for a single file for Gemini. Now you can upload up to ten images, PDFs or other files at once and ask Gemini to make sense of the mess.
AI Image Imagination
You may be wondering how Gemini’s editor will prevent people from exploiting its ability to make depths of real people or events for less than benign reasons. Google is eager to show that the company has been thinking about it. Therefore, each AI-edited image does not get one but two watermarks. One is visible and you use Google’s visual time, which can only be detected with software. There are also filters driven by human feedback that blocks ethical dice requests.
The option for editor and expanded upload does not break new grounds, but they add depth to Gemini. It’s not just about what Gemini can tell you it’s about what it can help you do. Google is investing a great effort to build Gemini in the kind of rounded, versatile tool sets that people are comfortable with trusting.
Instead of thinking about Gemini as a pure digital notetaker or search engine with a sense of humor, Google wants people to see Gemini as a partner in creative and productive tasks. We are still a way away from a world where you ask Gemini to “design a birthday card and bake the cake”, but it’s closer than you might think. Until then, it is a pretty good start to be able to throw ten files on Gemini and make it answer with something coherent while also placing a hat on your dog.
