Google has debuted Imagen 3, its highest quality text-to-image generation model yet, at Google I/O, happening right now.
Imagen 3 can create visuals with incredible detail, realistic lighting and fewer distracting artifacts, says Google, creating quick sketches to high-res photos.
Some examples were shared and it’s crazy how these look so real thanks to AI. The prompt, “A photo of a man with short hair and beard smiling at the camera. The background is blurry and it shows trees and buildings in light colors,” resulted in the following:
For the image at the very top of this article, the prompt was, “View from above, panoramic view of stunning river canyon with threes, overlooking water and green mountains. Pastel colors.” Impressive stuff.
Look at some more of the sample images below. Can you tell that these were created with AI?
Other AI image generators include the likes of OpenAI’s DALL·E 3. This is only just the beginning. Scary to think how much better than can get in a couple of years. We’ll never know what’s real or fake anymore!
Want to see more of our stories on Google?
P.S. Want to keep this site truly independent? Support us by buying us a beer, treating us to a coffee, or shopping through Amazon here. Links in this post are affiliate links, so we earn a tiny commission at no charge to you. Thanks for supporting independent Canadian media!
