I created these images using just my voice and the new Gemini feature. I’m impressed with the results

Google has just implemented the Image 3 engine in Gemini, opening up the ability for anyone using this artificial intelligence to create images. This AI can be used on the web, but its potential on mobile seems pretty wild to me. In my case, Gemini is a replacement for Google Assistant, so I just need to press the power button to activate it.

By opening Gemini directly, I can give it instructions in my voice without having to type in a prompt. What I didn’t expect was that I would press a button and tell it to “create an image of a Mercedes SLR McLaren on a race track” and it would create it perfectly.

Image 3 is a new version of the AI ​​model that Gemini will now use to create images. This is the most recent version, and according to Google, it improves on these three components compared to previous versions:

• The images have much more detail and fewer defects.
• The images are much more realistic than before.
• You can now create images with many more styles.

Using Image 3 in Gemini is a breeze. You just need to download the Gemini app from the Play Store and generate an invitation. You can write this, but doing it with your voice is much more convenient.

As an avid car lover, I asked Gemini to create an image of a Mercedes SLR McLaren on the highway. I chose this model because it is very specific in terms of design and, to my surprise, it recreated it almost perfectly. You can still tell it’s an AI-generated image, but for a photo created in five seconds by my voice, that’s not too bad.

In the second image I created something simpler: a dog and a cat walking together. The bokeh he creates is simply stunning, and in terms of sharpness the image is brutal.

To complicate things a little and see how you interpret styles, I asked you to show a New York street illuminated and in a Cyberpunk style. The result, again, is surprising.

To cap off the holidays, I asked you to submit an image of an iMac on your desktop with the word “Xataka” in the wallpaper. Text generation is a problem for many free AIs. This is not the case with Image 3. It also has no problem creating brand logos, although it’s not that great here.

Image | Hataka

In Hatak | 19 pages and services to create images from scratch using artificial intelligence