Google introduced Imagen 2 language model to Gemini, allowing users to generate images. After a controversy over AI-generated images, the feature was restricted for images of people. Google plans to improve it before enabling. Here's a step-by-step guide to using Google Gemini's image generation feature.
Earlier this month, Google Imagen 2 language model that brough AI-image generator feature to Gemini (formerly Bard). With the update, Gemini on the web as well as the newly announced Android app along with
Google app
on iOS can now generate images with the given prompt.
How image generation works in Gemini
As mentioned, the
AI image creator
feature on Gemini is powered by the Imagen 2 language model and it allows users to enter simple prompts on Gemini and based on its Google’s AI tool creates multiple images.
Users also get the option to create more options.
Google restricted the image generation ability amidst the latest controversy
Several users reported instances where AI-generated images displayed people of color in response to searches such as "generate a picture of a Swedish woman" or "generate a picture of an American woman."
In response to this, Google mentioned in the official blog post that “This wasn’t what we intended. We did not want Gemini to refuse to create images of any particular group. And we did not want it to create inaccurate historical — or any other — images. So we turned the image generation of people off and will work to improve it significantly before turning it back on. This process will include extensive testing.”
However, Gemini can still generate the images as long as the text prompt isn’t about creating images of people. If you want to get Gemini’s images generator a try, here’s our step-by-step guide:
Steps to create images using Google Gemini on computer, Android and iPhone
On computer
- Go to gemini.google.com in your web browser.
- Type an image prompt into the text box. Get creative and descriptive with your prompts for better results. Some examples: "an astronaut riding a horse on Mars", "a cute baby panda eating bamboo," etc.
- Hit "Generate" and Gemini will instantly create a gallery of AI images based on your prompt.
- Click "Generate more" below any images you like to get additional variations.
- Click any thumbnail image to open a full size version. Use the on-screen arrows or click "Show previous image/Show next image" to scroll through the images easily.
This method also works on all devices that has a web browser. You can use any browser to visit Gemini website and follow the above instructions to create AI images.
On Android via Google Gemini app
- Open the Gemini app on your Android phone.
- Type an image prompt into the text box.
- Tap "Generate" and swipe through the results.
- Tap a thumbnail to view any image larger.
- Tap the on-screen "Back" button to return to your image gallery.
On iPhone and iPad using Google app
- On your iPhone, open the Google app.
- Select the Gemini tab at the top.
- Type a prompt into the text box.
- Review the AI images and tap "Generate more" for additional options.
- Tap any thumbnail to open a full size version of that image.
- Tap the on-screen "Back" button to exit the full image view.
English (US) ·