Skip to main content

How to use DALL·E 2 to create jaw-dropping AI art

A page from the DALL·E 2 prompt book
(Image credit: The DALL·Ery GALL·Ery)

Wondering how to use DALL·E 2? The makers of the AI art generator have just announced that they'll be massively expanding access to DALL·E 2 in the next few weeks as they launch the platform in beta with a new credit-based model. So finally those who are already on the waiting list (apparently over a million people!) may be able to use DALL·E 2. But there will now be a cost involved.

DALL·E 2 has been making waves since it was first revealed back in April because it looks like it might be the most advanced AI art generator yet. And while some people are understandably concerned about where AI might leave human creativity, some artists and designers have been learning how to make the tool work for them.

How do you use DALL·E 2? The tool generates art based on text prompts. On the face of it, that couldn't be more simple – you type in what you want, and DALL·E will create the artwork. In reality, though, it appears the results can be a little haphazard and that can be useful to learn how to hone your prompts to increase the likelihood of getting the result you want. That's where a new DALL·E 2 prompt book comes in. If you prefer to create your own original work the traditional way, see our guide to the best graphic design software; otherwise, read on to learn more about how to use DALL·E 2 and how to access DALL·E 2.

How to use DALL·E 2

DALL·E 2 has a simple premise. You type in a descriptive prompt of up to 400 characters, for example "an astronaut riding a horse in an impressionist style", and AI magic will create the image. However, anyone who's tried AI art generators has probably found that if you type the first text that occurs to you, the results can be a little – erm – weird. But now a handy DALL·E 2 prompt book provides some advice on how to phrase the prompts to get the results you want.

Created by Guy Parsons and published by the AI art website the DALL·Ery GALL·Ery, the DALL·E 2 prompt book (opens in new tab) is a visual resource designed to inspire your own creations using DALL·E 2, and it offers some valuable pointers on how to get the most out of the AI art generator.

A page from the DALL·E 2 prompt book

The DALL·E 2 prompt book shows examples of parsing for photography prompts (Image credit: The DALL·Ery GALL·Ery)

The 82-slide guide covers techniques for eliciting the results you want from DALL·E 2 It covers aesthetics and vibes, recommended adjectives to use to get the feel or composition you're after and tips on everything from photography to creating painterly portraits and landscapes, film and illustration styles, historic art styles and 3D art. For photography, it suggests including proximity, angles, lighting quality and even lens-type in the prompt. For illustration, it provides examples of different styles, media and textures. It also shows how you can use styles from art history to get interesting results.

The guide points out that even the creators of DALL·E 2 don't know what the tool knows and doesn't know. Instead, users have to work out what it's capable of doing and how to get it to do what they want. One piece of advice is to be specific – state whether you want a close-up image or a particular angle. And remember that an adjective without further definition could be interpreted in different ways – to influence the whole look of an image or something as specific as the style of dress of the subject.

It's unlikely that DALL·E 2 is going to give you the results you want the first time. But the prompt book also shows how to edit images by writing new prompts for specific elements within them. It also shows how you can use DALL·E 2 to combine separate images. 

We've not had access to the tool ourselves, but we have to admit that some of the results look scarily impressive. Our take, for now, is that shouldn't be putting any artists out of work, but rather that there may be potential for creatives to make the tool work for them. For that, this new prompt book should be a useful resource for any creatives who've managed to gain access to the AI tool. If you're out of the loop, here's some more details on the tool.

What is DALL·E 2?

DALL·E 2 is a text-to-image AI art generator based on machine learning that's been provoking both horror and awe online (see our pick of the weirdest AI art created by DALL·E 2). Created by the artificial intelligence company Open AI, it's a generative tool, which means it can generate art from scratch as well as create edits or variations of existing work. It doesn't actually 'know' what it's creating but it makes assumptions based on the massive database of 650 million image and caption combinations that it's already been fed. 

The name is a portmanteau of 'Dali' (as in Salvador) and Pixar's 'WALL-E'. As the name suggests, this is the second iteration of the tool, and it seems to be a major improvement on the first, which tended to produce grainy images, and take a long time too. 

It's by no means the only generative AI art creator to work based on text prompts. Artbreeder has recently launched Artbreeder-collages, which blends text prompts with a collage-like design process. What appears to potentially set DALL·E 2 apart is that the results appear to avoid the uncanny valley effect often associated with AI art.

A variation created in DALL-E 2

DALL-E 2 can be used to generate original art or to create edits or variations of pieces uploaded to the platform (Image credit: OpenAI)

Is DALL·E 2 available to the public?

Until now the makers of DALL·E 2 have been selective about who can use the tool, granting free access by invite only. There's a waiting list, and Open AI says that around 100,000 people have been given access so far. However, the company has just announced that DALL·E 2 is now in beta (opens in new tab) and that it expects to expand access significantly over the next few weeks into August. It says that it will give access to a million people (and the wording suggests that this isn't the entire list of people waiting, so that must be some waiting list!)

The catch? DALL·E 2 will no longer be completely free to use. Instead, users will be given a limited number of monthly credits, with the option to pay to top them up (see below). It's still not clear when DALL·E 2 will be made completely public, so for now you can join the waiting list on the DALL·E 2 website and hope that yo might be included in the 1 million people who get access over the next month.

Is DALL·E 2 free?

OpenAI has been giving select people completely free access to DALL·E 2 since it opened limited access to the platform in April, but it's now announced a credit-based structure as it prepares to open wider public access for the beta version.

Now new DALL·E 2 users will be given a limited amount of free credits that they can put towards generating, editing or creating a variation of an image or creating a variation of an image (new image generations return four images; edits and variations three). 

Credits will be refilled each month but on a descending scale: 50 in the first month and then 15 a month after that. Users will be able to buy additional credits at a price of $15 for 115 credits (enough to generate 460 images). OpenAI has invited artists who need financial assistance to apply (opens in new tab) for subsidised access for artists who need financial assistance.

Is there a free DALL·E 2 alternative? Yes, there are several free AI art generators available. As well as Art Breeder-Collages, which we mentioned above (currently in beta), we've also been pretty amazed by DALL-E mini – now called Craiyon and Stable Diffusion.

An image of a fox in a field created in DALL-E 1 vs DALL-E 2

An example of how DALL·E 1 vs DALL·E 2 compare for the prompt "a painting of a fox sitting in a field at sunrise in the style of Claude Monet" (Image credit: OpenAI)

Why is DALL·E 2 access limited and what can you create in DALL·E 2?

Aside from the fact that restricted access has helped generate a lot of hype, DALL·E 2 has not yet been made available to everyone because it's still being tested and developed. Part of that has involved placing checks and restrictions on what people can create in DALL·E 2.

OpenAI says that it's able to start expanding access now thanks to changes in its policies and advances in mitigating "bias and toxicity" in images generated by the platform. The company says that this week it made a change that will push DALL·E 2 to generate images of people that “more accurately reflect the diversity of the world’s population” if race or gender is not specified in the text prompt.

It says that it's also taken steps to ensure that the platform rejects image uploads that contain realistic-looking human faces or the likeness of public figures, such as politicians and celebrities. OpenAI says it doesn’t allow DALL·E 2 to be used to create images that could cause harm, for example, images showing self-harm, hateful symbols or illegal acts. It stressed that it has both automated and human monitoring systems to prevent this, as well as to prevent DALL·E 2 from memorising faces that appear a lot online, however it recognises that there's more work to be done in this area.

Can you use DALL·E 2 for commercial use?

Until now OpenAI had prohibited commercial use of images generated by DALL·E 2, but in the beta version, it's now giving “full usage rights” for images created with the platform. That includes the right to sell and reprint images and to use them on merchandise.

An image of an astronaut on a horse created by DALL-E 2

(Image credit: OpenAI)

How can you tell if an image was created by DALL·E 2 AI?

Images generated by DALL·E 2

You can tell is an image has been created by DALL·E 2 because they contain a signature that looks like a row of coloured squares at the bottom right of the image (assuming the image hasn't been cropped. See the example above.

Read more:

Thank you for reading 5 articles this month* Join now for unlimited access

Enjoy your first month for just £1 / $1 / €1

*Read 5 free articles per month without a subscription

Join now for unlimited access

Try first month for just £1 / $1 / €1

Joseph Foley
Joseph Foley

Joe is a regular freelance journalist and editor at Creative Bloq. He writes, news and features, updates buying guides and keeps track of the best equipment for creatives, from monitors to accessories and office supplies. A writer and translator, he also works as a project manager at a design and branding agency based in London and Buenos Aires, Argentina, where he manages a team of designers, photographers and video editors. He enjoys photography and wellness and also dances tango.