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.
OpenAI recently added DALL-E 3, its most powerful version of an artificial intelligence image generator to date, to ChatGPT Plus and Enterprise subscriptions. Since then, paid ChatGPT subscribers can access DALL-E 3 within the AI chatbot, as it's yet to become available through OpenAI Labs.
DALL-E 3 is also available through the Bing Image Creator, which gives users the chance to access the AI image generator for free through a Microsoft account.
How to create AI images using DALL-E 3 in ChatGPT
What you'll need: As stated above, using DALL-E 3 in ChatGPT requires a Plus or Enterprise because DALL-E 3 is only available within GPT-4. A Plus subscription costs $20 per month, while the cost for the Enterprise tier varies depending on the size of the organization. You can learn more about subscribing to ChatGPT Plus or read on if you're already a subscriber.
1. Log in to ChatGPT
Go to ChatGPT's website to log in, Chat.OpenAI.com. If you haven't signed up for ChatGPT Plus, select Sign up and enter your account information.
2. Switch to GPT-4
Click on the dropdown menu that says GPT-3.5 and select GPT-4.
For example, I'm writing "a photo of a blue alligator driving a spaceship with planet Earth in the background."
My prompt includes specifics about the subject, down to the color of the alligator, what I want in the background, and the style, which is a photo. You can choose whatever style you want, like a painting, watercolor, 3D render, one-line drawing, etc.
4. Download or regenerate your image
Click on the image to view it and download it.
If you'd like DALL-E 3 to have another go and regenerate an image using the same prompt, click on the refresh button below the image.
Can I access DALL-E 3 without a ChatGPT Plus subscription?
DALL-E 3 isn't available in OpenAI Labs like DALL-E 2 has been for over a year. But the company advised it would be adding the latest version to Labs this fall.
For now, you can use DALL-E 3 for free in the Bing Image Generator. Just log in or create a Microsoft account and start creating pictures.
Does DALL-E 3 have a limit?
Within ChatGPT Plus, DALL-E 3 has the same limits as GPT-4, which is 40 messages in three hours.
The Bing Image Creator doesn't limit DALL-E 3, but it gives you 'Boosts,' which are tokens that let you create images faster. Each account starts with about 100 boosts. After these boosts run out, your images will take longer to generate.
Disclaimer: You should consider the legal consequences (e.g. copyright) of using AI-generated images before implementing them into your work.