NAIROBI, Kenya- In May, Google introduced its third-generation image generation model, Imagen 3, and by August, teased a global release.
Now, it’s official: Google has rolled out Imagen 3 to all Gemini users worldwide, opening up a new realm of AI-generated visuals.
This latest iteration boasts sharper details, more vibrant colors, and a marked reduction in the flaws seen in earlier versions.
So, what’s the big deal? Well, Imagen 3’s ability to handle text within images is turning heads—something competitors like DALL-E and Adobe Firefly have famously struggled with.
If you’re itching to test out these new features, getting started with Imagen 3 is pretty straightforward.
Fire up Gemini on either your desktop or mobile device. From there, simply use prompts like “draw,” “generate,” or “create,” and describe the style you’re aiming for.
Remember, the more detail you give, the closer the image will be to your vision. As the platform works its magic, you’ll see the message: “Creating your image with Imagen 3.”
But, here’s the catch: If you’re using the free version of Gemini, you won’t be able to generate images featuring people. To unlock that ability, along with a suite of other premium features, you’ll need to subscribe to Gemini Advanced.
As impressive as Imagen 3 is, it does bring up an important point: the need for clearer labeling of AI-generated content.
It’s becoming harder to tell what’s real and what’s computer-generated. The risks of spreading misinformation are growing, and global regulators need to step in.
For example, the European Union recently introduced the EU AI Pact, a voluntary agreement between tech companies and the EU aimed at promoting responsible AI development.
Whether this pact will truly impact the AI landscape remains to be seen, but it’s a step in the right direction. Governments worldwide must follow suit if we’re going to keep the line between fact and fiction from blurring even further.
