How to use DALL-E 2 to generate AI images

As AI image generation becomes more and more popular, many people are looking for easy ways to do it such as: B. how you can use DALL-E 2 to generate AI images on your own computer. DALL-E (yes, named after WALL-E as well as Salvador Dali) and its successor DALL-E 2 brought their own brand of AI imaging to the web, developed by OpenAI, but access to the software was severely restricted.

That changed in the summer of 2022 with a limited public beta and a few months later with the full beta now available for everyone to try. Here you can log in, use the AI ​​generator and master image generation tricks.

How to use DALL-E 2

Step 1: Sign up for OpenAI. If this is your first time, you’ll need to create an account to sign up, but it’s completely free. You also have the option to sign up through Google or Microsoft if you want to save some time. OpenAI requires two-factor authentication, so have your phone ready when you get started.

Step 2: When registration is complete, Open AI will introduce you to DALL-E 2. Choose Continue to start with the AI. OpenAI then explains its credit process or how you can use DALL-E 2 over time.

When you sign up for the first time, you get 50 free credits to experiment with for your first month. After that, you’ll get an additional 15 credits to use each month. Each credit represents a single DALL-E 2 request, like generating an image, so you can get an idea of ​​how many tries you’ll get. You can always buy additional credits through the OpenAI store: $15 gives you 115 credits to work with.

Step 3: On the DALL-E 2 home screen you will see a few different options to get started. You can enter your own description, upload an image for the AI ​​to edit according to your instructions, or choose Surprise me, which automatically generates a description designed to play well with the AI. Remember that you only have a limited number of credits, so plan carefully. First, let’s assume that you enter a description to achieve a specific result.

Step 4: Enter your description. You have 400 characters at your disposal, so take your time and be specific. DALL-E 2 plays well with artistic imagery, so don’t be afraid to ask for a painting, stained glass, digital art, or any other specific medium you’d like to try. Choose to generate when you’re done

Step 5: For each request, DALL-E 2 generates several different images for you to choose from. Find one you like and use the buttons in the top right corner to either favorite it for a later look or download it now.

Step 6: If the picture is not quite what you want, you can try to select it variations, which generates a new selection based on the selected image. Or you could go back and try tweaking your phrase to get a different result.

Step 7: Sometimes changing just one or two different words or specifying a different medium can make a big difference. Think about how you want the image and try something new if necessary. The results may be unexpected, but that’s half the fun.

Tips for using DALL-E 2

If you want to use DALL-E 2 seriously, e.g. For example, for a school assignment or an art project, you might want to research the best ways to use it first—and save money on credits as a result. Luckily, Guy Parsons’ Dallery Gallery blog already has an excellent guide coming out in 2022 for new users. It’s a bit long with over 80 slides, but it walks you through the basics so you’re ready to generate exactly the type of AI imagery you want. Some important tips are:

• Prompts don’t have to be long, they can be as short as a few words. What’s even more interesting is that it can also be a set of emojis that DALL-E 2 will try to interpret as accurately as possible (i.e. your eggplant emoji is a real photo of an eggplant).

• When we mentioned that DALL-E 2 is artistically oriented, we mean that the AI ​​processed a lot of art. This means that certain tricks can produce interesting results. The mention of a specific type of art encourages DALL-E 2 to also draw inspiration from the time when that style was fashionable, such as B. “Surrealism”. Other examples include dieselpunk, post-apocalyptic, and cyberpunk. Or you could jump right in there and add something like “the 1950s” to your description to get a specific era.

• DALL-E 2 also knows a lot about photos. Photographers should not hesitate to include specific views, angles, distances, lighting, and photographic techniques (or even lenses) to see how DALL-E 2 responds.

• It is technically against DALL-E 2 policy if you upload and use a prompt photo that you do not have the rights to. If DALL-E 2 has processed many other works by that particular painter, photographer, etc., it may be able to create a piece inspired by them if you include their name in the description. This extends to all kinds of proper nouns, like popular cartoons or movies.

• AI generators typically fight with faces unless they have a very specific prompt. If the face in your picture is just too weird for you, you can try again and add an additional description for the face, e.g. B. the type of expression you want, where the face is looking, etc.

• When you upload an image, there’s a lot you can do with cut and paste, whether you want to cut out a specific subject and place it in a new setting, or you want to remove unwanted objects from an image and recreate it.

Editor’s Recommendations