X
Innovation
Why you can trust ZDNET : ZDNET independently tests and researches products to bring you our best recommendations and advice. When you buy through our links, we may earn a commission. Our process

'ZDNET Recommends': What exactly does it mean?

ZDNET's recommendations are based on many hours of testing, research, and comparison shopping. We gather data from the best available sources, including vendor and retailer listings as well as other relevant and independent reviews sites. And we pore over customer reviews to find out what matters to real people who already own and use the products and services we’re assessing.

When you click through from our site to a retailer and buy a product or service, we may earn affiliate commissions. This helps support our work, but does not affect what we cover or how, and it does not affect the price you pay. Neither ZDNET nor the author are compensated for these independent reviews. Indeed, we follow strict guidelines that ensure our editorial content is never influenced by advertisers.

ZDNET's editorial team writes on behalf of you, our reader. Our goal is to deliver the most accurate information and the most knowledgeable advice possible in order to help you make smarter buying decisions on tech gear and a wide array of products and services. Our editors thoroughly review and fact-check every article to ensure that our content meets the highest standards. If we have made an error or published misleading information, we will correct or clarify the article. If you see inaccuracies in our content, please report the mistake via this form.

Close

How to use Microsoft Designer's Image Creator (formerly Bing Image Creator)

It's free, there's no waitlist, and you don't need to use Edge to access it. Here's everything you need to know to use Microsoft's AI art generator.
Written by Maria Diaz, Staff Writer
Reviewed by Alyson Windsor
designer

An AI-generated photo created with Microsoft Designer using the prompt "a photo of a cool robot taking a picture with a DSLR camera in a photography studio."

Maria Diaz/ZDNET via Image Creator from Designer

As the use of different artificial intelligence (AI) tools has exploded over the past year, we've seen the development of generative AI sprouting everywhere. OpenAI releasing ChatGPT in November 2022 quickly led to Google, Microsoft, and Meta all coming up with their own AI chatbots: GeminiCopilot, and Meta AI

Microsoft also released an AI image generator within Bing powered by DALL-E 3, the latest of OpenAI's visual projects. Since then, the company has renamed this tool from Bing Image Creator to just Image Creator, albeit under the Microsoft Designer umbrella.

How to use: Midjourney | Craiyon AI | DALL-E 2 | Stable Diffusion | DALL-E 3 in ChatGPT

Using Image Creator is possible through Copilot, formerly known as Bing Chat, or directly on the tool's website. It's as easy as prompting an AI chatbot like ChatGPT. 

How to use Microsoft's Image Creator

Dodo photo

Would anyone believe this is a real Dodo Bird randomly found wandering about? Image created with Image Creator from Designer.

Maria Diaz via Bing Image Creator/ZDNET

What you need: Using Image Creator only requires access to Bing.com. You don't need an OpenAI account. You can access Image Creator via Copilot in the new Bing or by visiting bing.com/create.

Also: I'm taking AI image courses for free on Udemy with this little trick - and you can too

We'll cover how to create images directly on the Image Creator website, but you can find how to generate images in a chat with Copilot in the FAQ (below).

1. Go to the Image Creator from Designer and log in

You don't need Microsoft Edge to access the Image Creator from Designer, but you do need a Microsoft account. Go to bing.com/create and click on Join & Create to log in to your Microsoft account and access the image generator. 

Join and create

On Image Creator's homepage, click Join & Create.

Screenshot by Maria Diaz/ZDNET

2. Enter your prompt

Next, enter a description of the image you want Image Creator to generate for you. Just like when using an AI chatbot, be as descriptive as possible to ensure your result is accurate.

After you enter your prompt in the text area, click Create. 

Enter prompt

Enter your prompt in the text area.

Screenshot by Maria Diaz/ZDNET

For this prompt, I'm going to request the following: "photo of a dodo bird sitting on a concrete floor of a brightly lit home in the tropics." Then I click Create and wait for my images to be generated.

3. View your results

Once your images are ready, it's time to check the results. DALL-E 3 and Image Creator will typically display four generated images for each prompt. 

Also: How to use DALL-E 3 in ChatGPT

They're not always great, as the free AI image generators are often not advanced enough to create truly lifelike images. You may see some errors in details, such as a person's fingers or eye positioning, or the keys on a computer keyboard, for example. 

As you can see below, the generated images capture almost exactly what I prompted Image Creator to create. Asking it to create an image of an extinct bird was a big challenge as DALL-E 3 isn't trained on many different pictures of dodo birds due to them going extinct in the 17th century. There are some resemblances to a pelican and a toucan in the images put out by Image Creator, but it's close enough.

Results

Image Creator's preview results were created with the prompt I entered (highlighted at the top).

Screenshot by Maria Diaz/ZDNET

4. Download your image(s)

After looking through the generated images, I downloaded the picture below. Clicking on an image will expand it and give you the options to Share, Save to your account, Download, or provide Feedback. It's worth noting that you can download one, all, or none of the images. 

In a new feature since merging the tool with Designer, Microsoft now lets you customize the image. Clicking Customize will open Microsoft Designer.

Dodo image - Bing

This was my favorite photo of the four.

Screenshot by Maria Diaz/ZDNET

FAQs

Can I create images using Microsoft Copilot or Bing Chat?

There are two ways to use Image Creator. You can generate images by going to bing.com/create, as detailed above, or create images using GPT-4 in Copilot, previously known as Bing Chat.

Creating images in Copilot with GPT-4

I asked Copilot with GPT-4 to create a photo of "a lazy panda sleeping in a room with gold accents and forest green curtains."

Screenshot by Maria Diaz/ZDNET

Here's how to ask Image Creator to create an image right from the chat window; the same process works in Microsoft Copilot:

  1. Go to copilot.microsoft.com.
  2. Log in with your Microsoft account.
  3. Write your prompt; it can begin with phrases like "create an image" or "generate a photo," but it's not necessary. Copilot with GPT-4 typically recognizes your intent.

Copilot can create images in any conversation style, whether set to Creative, Balanced, or Precise. 

Also: How to use Copilot (formerly called Bing Chat)

One of the pros of using Copilot to generate images is that you can ask follow-up questions to have Copilot adjust the image. Copilot proposes questions like, "Can you make the monkey wear a hat?" and "Change the color of the Vespa to blue."

How do you write prompts to create images using AI?

The more specific you are in your prompts, the better. Think of the prompt as a detailed description of the image you have in mind. Include adjectives, nouns, and verbs to describe the image and what the subject is doing -- even styles are encouraged. If you ask the AI bot to create "a photo of...," you'll get a different result than if you say to create a cartoon, a painting, or a 3D render, so the image style is important.

Bing Image Creator template

This is the best way to build a successful Image Creator prompt.

Screenshot by Maria Diaz/ZDNET

Here's how Image Creator recommends you format your prompts: Adjective Noun Verb Style. 

In the example above, that would be "Fuzzy creature wearing sunglasses, digital art." 

You can also use different terms to describe the style, such as impressionism, cubism, abstract, etc. 

Do I own AI-generated images?

The latest line from the United States Copyright Office is that AI-generated images are not protected under current copyright laws because they are not the product of human authorship. Images generated with Designer have an invisible watermark to denote they are AI-generated content. The watermark includes Microsoft's information and the date and time the image was generated.

AI image generators have caused controversy because they are AI bots trained on images found online and created by someone else. While the art you produce using an image creator tool is unique, it's generated with the influences of millions of artists on the internet.

Also: Have 10 hours? IBM will train you in AI fundamentals - for free

The copyright ruling could, however, change in the near future.

Is Image Creator free?

Microsoft Designer's Image Creator is free at this time, though you can pay for more boosts if you run out. Boosts are like credits; each prompt you give to create an image will cost you one boost.

Also: I've tested a lot of AI tools for work. These are my 5 favorite so far

Users used to get 25 boosts when they first started using Image Creator, but Microsoft has since increased the amount to 100. 

Once you run out of boosts, Image Creator will take longer to generate images after being prompted. Instead of 10 to 30 seconds, the tool can take up to five minutes.

Is Image Creator from Designer the same as DALL-E?

DALL-E 3 and Image Creator are not the same tool. As with GPT-4 in Copilot, Microsoft is incorporating the more advanced DALL-E 3 into its image creator. DALL-E 3 is available for ChatGPT Plus subscribers as well. Currently, Image Creator is the only way to use DALL-E 3 for free.

Is there a waitlist to use Image Creator?

There is no waitlist to use the Image Creator at this time. You can access it by logging into the website with your Microsoft Account. 


Disclaimer: You should consider the legal consequences (e.g. copyright) of using AI-generated images before including them in your work.    

Editorial standards