How to use Microsoft Image Creator to generate and edit stunning AI images for free - Related to game-changer, a, gemini's, firefox, images

Firefox expands access to popular AI chatbots right from the sidebar

Firefox clients can now tap into their favorite AI directly from the browser. Currently rolling out to all Firefox clients with version 135 is a sidebar feature that grants access to several different AI chatbots. The list includes Anthropic's Claude, OpenAI's ChatGPT, Google Gemini, HuggingChat by Hugging Face, and Le Chat Mistral.

The AI access has been available in Firefox since last September with version 130 but only on an experimental basis. Now it's an official feature built into the browser for anyone to use.

Also: The best AI chatbots of 2025: ChatGPT, Copilot, and notable alternatives.

The first time you do this, you'll be prompted to sign in to each AI you want to use. You'll need regular accounts with the services you wish to access. But this will work whether you use them for free or via paid subscriptions. After you're signed in, you're able to use all the core elements of the AI.

For example, signing in with my ChatGPT Plus account lets me choose among the different models, submit a prompt, generate an image, and view my chat history. Logging in with my Google Gemini Advanced account provides all the available models from Flash [website] to Flash [website], allows me to speak my request, and lets me upload an image or other file for analysis. My current free plan with Anthropic's Claude also offers all the standard aspects.

Also: How I made Perplexity AI the default search engine in my browser (and why you should too).

The other two AIs in the mix -- HuggingChat by Hugging Face, and Le Chat Mistral -- may not be as well known. HuggingChat is an open-source alternative to ChatGPT, while Le Chat Mistral is a French-based AI still in beta.

Among the AIs missing from Firefox's list is Copilot. But that's hardly surprising since Mozilla competes with Microsoft in the browser arena, and Microsoft Edge itself offers Copilot access through its sidebar.

Firefox's slice of the browser market has dwindled over the years, putting it behind Chrome, Edge, and mobile Safari. But Mozilla continues to innovate and add new capabilities to its browser -- a sign that there's still plenty of life left in it.

Since DeepSeek challenged OpenAI two weeks ago, the open- vs. closed-source AI...

'ZDNET Recommends': What exactly does it mean?

ZDNET's recommendations are based on many hours of t...

We all have to deal with contracts and agreements as consumers or business professionals. How...

How to use Microsoft Image Creator to generate and edit stunning AI images for free

Generative AI is super popular right now. Since OpenAI released ChatGPT in 2022, countless tools and chatbots have popped up. For example, Microsoft launched an AI image generator within Bing, powered by DALL-E 3, one of OpenAI's visual projects. It was originally called Bing Image Creator but is now called Image Creator under the Microsoft Designer umbrella.

Image Creator lets you generate AI images from text prompts. It's easy to use, whether you're accessing it through Copilot or directly on its website. Just type in a description, and the AI does the rest, creating a set of images based on your prompt. Microsoft says it takes responsible AI seriously -- blocking harmful prompts and adding invisible watermarks to AI images.

Also: I tested this viral AI image generator, and it does text well.

You can also redeem Microsoft Rewards for more boosts if needed.

With support for over 100 languages, Image Creator is a powerful tool for most casual consumers. If you're ready to try Image Creator, our guide displays you exactly how to get started with generating images today.

What you need: To use Image Creator, all you need is access to [website] No OpenAI account required, but you do need a Microsoft account. You can access Image Creator through Copilot or through its website. We'll cover in detail how to create images on the Image Creator site, but you can check the FAQ below for instructions on using Copilot.

For example, I requested the following images: "Photo-realistic image of a three-year-old toddler with coily curly blonde hair that goes past her shoulder blades. Show her lying on a dark wood floor watching an 85-inch TV. She's wrapped in a fluffy white blanket and holding a green alien stuffed animal."

"Two black labs and a husky sitting in a snow-covered backyard."

"Photo of a dodo bird sitting on a concrete floor of a brightly lit home in the tropics." Show more.

Can you create images with Microsoft Copilot?

Yes. There are two ways to use Image Creator. You can generate images by going to [website], as mentioned earlier, or you can use Copilot ro create images directly in a chat.

Here's how to create an image right from the chat window:

Go to [website] Log in with your Microsoft account. Write your prompt. You can start with phrases like "create an image" or "generate a photo," but it's not required. It usually picks up on what you mean.

A big perk of using Copilot to generate images is that you can ask follow-up questions to tweak the image. Copilot will suggest things like, "Can you make the dodo wear a hat?" or "Change the color of the feather to blue."

Can you edit the AI images after downloading them?

Yes, once you download your image from Image Creator, you are free to edit it using other software or photo-editing apps, but you won't be able to edit it directly in Microsoft's Image Creator once it's been saved. You can, however, use the customize tool to make adjustments like cropping, rotating, or auto-enhancing before downloading the image.

How to write good prompts for AI image generation.

The more specific you are with your prompts, the enhanced the result.

Think of the prompt as a detailed description of the image you want to create. Include adjectives, nouns, and verbs to explain the image and what the subject is doing -- styles are also a great addition. For example, if you ask the AI bot to create "a photo of...," you'll get a different result than if you specify you want a cartoon, a painting, or a 3D render. The style really matters.

Also: The five biggest mistakes people make when prompting an AI.

Here are some prompt tips from Microsoft you might find helpful:

Creating an image with Image Creator is different from searching Bing. It works best when you're specific -- add details like adjectives, locations, and artistic styles ([website], "digital art" or "photorealistic").

Instead of just typing "astronaut," try: "A close-up photo of an astronaut in a glowing plasma suit, with the galaxy inside it, putting on their helmet, but you can't see their face because of the visor, realistic, film stock, bright colors."

Use the following format when writing your prompts: Adjective + Noun + Verb + Style. (For example, "Fuzzy creature wearing sunglasses, digital art.").

, purely AI-generated images aren't protected under current copyright laws because they're not the result of human authorship. Images created with Designer have an invisible watermark that presents they're AI-generated. This watermark includes Microsoft's info, along with the date and time the image was made.

Also: Is DeepSeek's new image model another win for cheaper AI?

AI image generators have sparked controversy because they're trained on images found online, many of which were created by other people. While the art you create with these tools is unique, it's still influenced by millions of images from across the internet.

Microsoft Designer's Image Creator is currently free to use, offering 15 daily boosts to speed up image generation. Each boost allows for faster processing of your image prompts. If you run out of boosts, you can still create images, but the generation process will take longer. To continue enjoying faster image creation, you can redeem Microsoft Rewards points for additional boosts.

For those seeking more boosts, Microsoft offers a Copilot Pro subscription, which provides 100 boosts per day. This subscription also includes other benefits across Microsoft 365 apps.

On Thursday, French lab Mistral AI launched Small 3, which the organization calls "the most efficient model of its category" and say......

When incorporated into business operations, AI's ability to act as an assistant in virtually every aspect of a professional's......

DeepSeek V3: A New Contender in AI-Powered Data Science.

How DeepSeek’s budget-friendly AI model stacks up against ChatGPT, Claude, and Gemini in SQL,......

Google Gemini's lock screen update is a game-changer for my phone

One of the biggest drawbacks to using Gemini as your default Android assistant is going away.

In a blog post today, Google detailed how Gemini extensions are now available from your phone's lock screen. While there isn't necessarily any new functionality, it is now easier than ever to access Gemini for getting quick answers, setting reminders, making calls, controlling smart devices, setting alarms, controlling media, and more.

Also: Gemini's Deep Research browses the web for you - try the Android app now for free.

Earlier this year, Google did expand Gemini to make phone calls and send messages from your lock screen, but this is a significant expansion in capability.

To start, you might need to enable Gemini on the lock screen. If you previously enabled Google Assistant on your lock screen, you should be fine, but if not, you'll need to open Gemini, tap your photo, go to the settings menu, and then select "Gemini on lock screen." From there, you'll see a toggle to "Use Gemini without unlocking."

There are several ways to open Gemini from your lock screen once it's enabled. You can use "Hey Google" as always (I found that method easiest, especially if you're utilizing it while driving), or you can use your device's normal method of firing up the assistant (usually long-pressing the power button). Either should open the Gemini prompt that lets you proceed with your query.

When Gemini opens, Google says it can handle most of your normal requests.

Also: Gemini Live is expanding and can now talk about what's on your screen.

I tried it out for myself by asking what time a local store closed. Gemini responded immediately with the address and closing time. I asked it for directions, and it opened Google Maps with the destination set -- all without unlocking my phone. I asked for a reminder in 30 minutes, and Gemini immediately added it.

Google does note that some things, like calendar events, access personal content, and will still need you to unlock your device. To test this, I asked Gemini from my lock screen to add something to my calendar. It asked for a name and time, then added it to my calendar. But when I asked Gemini what was on my calendar for today, it replied that I needed to unlock my device first.

Essentially, anything that's not tied to your personal messages or information, Gemini can now handle from your lock screen.

These changes should be available now to all Gemini customers.

Note: This blog was first . Following the paper’s publication in Science on 8 Dec 2022, we’ve made minor updates to the text to...

New AI system designs proteins that successfully bind to target molecules, with potential for advancing drug design, disease understanding and more.

Research From motor control to embodied intelligence Share.

Using human and animal motions to teach robots to dribble a ball, and s...