- The Model Context Protocol: Simplifying Building AI apps with Anthropic Claude Desktop and Docker | Docker
- This robot vacuum and mop performs as well as some flagship models - but at half the price
- Finally, a ThinkPad model that checks all the boxes for me as a working professional
- Why I recommend this Android phone for kids over a cheap Samsung or Motorola model
- My favorite USB-C accessory of all time scores a magnetic upgrade
How to use ImageFX, Google's AI image generator
With all the investment Google has made into artificial intelligence (AI), it’s not surprising the tech giant launched its own AI-powered image generator, ImageFX, earlier this year. ImageFX aims to rival OpenAI’s DALL-E 3, Midjourney, Microsoft’s Image Creator by Designer, and many others.
Also: The best AI image generators to try right now
ImageFX is powered by Imagen 2, the latest generation of Google’s text-to-image technology. Each image created with ImageFX is embedded with DeepMind’s SynthID, a digital watermark that is invisible to the naked eye. The watermark can be used to show the image was created by AI.
How to use ImageFX
Photo created using ImageFX with the prompt, “photo of a kangaroo in a colorful bakery looking at desserts in a display case with flowers and pastel colors.”
Radhika Rajkumar/ZDNET via ImageFX by Google
To access ImageFX, you’ll need to sign in to your Google account and, if it’s your first time using ImageFX, you’ll need to click through the AI Test Kitchen’s email settings. They’ll ask whether or not you’d like to receive marketing emails or research invitations.
You’ll also have to review the AI Test Kitchen’s privacy policy and terms of service.
Also: 6 ways to write better ChatGPT prompts
Google will give you a brief overview of ImageFX, explaining what it is and how AI-generated images can include mistakes, and remind you to respect the rights of others.
It’s important to be as detailed as possible when you enter a prompt for image creation. Try to imagine the image you want to see and then write a description of what you want.
It’s worth adding the image type you want, such as a photo, 3D render, drawing, etc. You can go as far as adding a style, like impressionism, abstract, vaporwave, etc.
Also: Six skills you need to become an AI prompt engineer
I’m using the prompt, “photo of a kangaroo in a colorful bakery looking at desserts in a display case with flowers and pastel colors.”
ImageFX will create up to four images with your prompt, and you can click on each one to copy the prompt or the image, download them, and share them. On the left side of the screen above the prompt field, you can toggle between the images to view them in a grid or one by one.
In our case, for some reason, ImageFX only generated one image for me.
Click the Edit Image button in the lower-left corner of the image to open the editor, where you can apply masks and enter descriptions of changes you’d like to make.
FAQs
Can ImageFX change an image it has created?
If you give ImageFX a prompt and don’t like any of the outputs, you can tweak your prompt on the left-hand side of the window and regenerate your image. In fact, Google creates dropdown menus on each keyword in your prompt:
In my example above, Google created dropdown menus on the bolded words from my prompt: “photo of a kangaroo in a colorful bakery looking at desserts in a display case with flowers and pastel colors.” For each one, Google gave alternatives — if I clicked on “colorful”, for example, Google suggested “monochromatic”, “neutral colors” and “muted colors”.
Is Google’s AI image generator free?
Yes, ImageFX is free, as is Gemini’s (formerly Bard’s) image generation capability. All you need to do to use Google’s AI image generator is to log in to a Google account.
