DALL-E Enters Beta, Invites One Million New Users to Try AI Art
DALL-E is growing significantly, and it may soon be your turn to create realistic AI art.
If you’ve seen a surreal image of three smiling chihuahuas in a taxi, an astronaut on a white horse, or a fox possibly painted by Monet, you can probably credit DALL-E, the artificial intelligence-powered image generator from OpenAI, which is finally going into beta this week.
Now in version two, DALL-E 2 (opens in a new tab) is probably one of the most talked about AI since HAL 9000 (opens in a new tab). His images, which are generated based on a natural language description provided to him, are realistic, hesitant and mind-blowing. They’re now good enough to be on the cover of a magazine (opens in a new tab).
Until recently, most people did not have direct access to DALL-E and instead had to satisfy their AI image cravings with DALL-E mini (opens in a new tab)a small scale counterfeit built by Craiyon.
Starting today, OpenAI invites up to one million new DALL-E 2 users from its waitlist (your author is on it), but not all at once. In a blog post, OpenAI writes that the process will unfold “over the next few weeks.”
Pay the AI
There is a small wrinkle (come to think of it, I would like to integrate this sentence into DALL-E). New DALL-E artists will receive 50 free credits to create images with 50 different natural language phrases. After going through the first 50, OpenAI will provide them with 15 credits per month. This means you can create 15 different surreal images per month. However, it can be a bit like the three wishes you get from a Genie: worrying about using a poorly crafted phrase that inspires lackluster DALL-E art, and knowing you only have 14 wishes left. .phrases for the month.
You can generate more images if you are willing to pay DALL-E. No, not in the blood and sweat of a budding artist, but in cash. $15 will buy 115 credits or 460 DALL-E image creations.
If you receive a DALL-E invite, you’ll be entitled to a number of useful features, including the ability to use DALL-E to edit images generated through the system or those you upload. You can, for example, upload a classic piece of art and have DALL-E generate variations based on the art. DALL-E 2 can also seamlessly add new elements to existing images. You tell it what you want to add and where you want to put it in the image. The edits will take into account shadows and highlights to make the new element look like it was still part of the original art.
As for where you will store your AI art, OpenAI offers to keep everything on the DALL-E platform. Maybe you can eventually host your own AI art gallery screenings.
Even though OpenAI charges for creating images beyond what you get for free, the nonprofit doesn’t seem interested in making a big DALL-E profit.
In the blog post, the company announced that you retain the rights to any images you generate through DALL-E, including those generated before the platform went into public beta. Now you can take that image of a dog on a bike eating an ice cream cone and post it on websites, or put it on T-shirts and mugs.
OpenAI expects DALL-E images to display on a wide variety of platforms.
“Users have told us that they plan to use DALL·E images for commercial projects, such as illustrations for children’s books, art for newsletters, concept art and characters for games, moodboards for design consulting and storyboards for movies,” OpenAI wrote in the post.
Before you start feeding photos of family, friends, politicians and celebrities, please be aware that DALL-E will automatically reject any attempts to create realistic images of real people, including celebrities and politicians.
The DALL-E 2 beta will also seek to spit out more diverse imagery “that more accurately reflects the diversity of the world’s population,” the post notes.
It is, of course, impossible to tell what people will feed DALL-E 2 and what kinds of results it will spit out. OpenAI seems determined to maintain control and run the platform without bias, but if the history of AIs has taught us anything, it’s that their ability to learn and adapt to new information makes them unpredictable. .
If you’re hoping for the chance to create your own AI art, you can always join the DALL-E 2 waiting list. (opens in a new tab)though you’ll surely be queuing up behind the millions of people who likely signed up when DALL-E first appeared a few months ago.