But now OpenAI, the company behind it, has announced that the waiting list is no longer there. Starting today (September 28), anyone can use DALL-E 2 and let their imaginations run wild by creating images generated by artificial intelligence. If you want to try it out, check out our article How to use the DALL-E 2 first.
DALLE-2 launched in beta in April and was quickly hailed as one of the most advanced AI image generators, especially when it comes to creating photorealistic images. It still has some issues with the nightmarish faces that other AI image generators suffer from, but overall it’s much more convincing (see this comparison of the best AI image generators).
The catch was that access to DALLE-2 was only possible by invitation via a waiting list, although OpenAI says it is currently used by 1.5 million people. But it’s over now. The platform is still in beta, but now anyone can use it by registering on the OpenAI website (opens in a new tab). However, some people report that it is not that simple. People responded on Twitter and Instagram to say that DALLE-2 is showing up as unavailable in their country or that they get an error when trying to register.
We have deleted the waiting list for DALL · E. Sign up and start creating right away! https://t.co/TCVDl1iMeUSeptember 28, 2022
Opening access seems more in line with the name of the company behind DALL-E. It seemed ironic that a company called OpenAI was restricting access to its product. Meanwhile, prices will remain the same as from July, when the credit-based system was introduced (see below for details).
Open Access seems fairer, and that means all creators can experiment with one of the most effective text-to-image generators, giving them a new resource to test new ideas and potentially speeding up the workflow. But it’s also a bit scary. The DALL-E 2 can create very realistic images, and the ban on editing real human faces has just been removed, which runs the risk that people’s images can be altered without their consent to create a deepfake or commit a scam.
Open Source Stability AI Stable Diffusion has faced criticism for its lack of restrictions that allowed users to create violent and pornographic content. Opening Access DALL-E 2 will now test OpenAI’s proprietary security features it claims are built in from the outset and further enhanced through “learning from real use”. Today’s blog post states that these improvements now enable Open Access.
The company says it uses a combination of automated and human monitoring to prevent prohibited content. Attempts to create images of public figures are prohibited and the dataset used to train the DALL-E 2 has been filtered to remove manifestly aggressive, sexual or hateful images. “We have made our filters more reliable in rejecting attempts to generate sexual, violent and other content that violates our content policy, and we have developed new detection and response techniques to stop misuse,” says OpenAI.
In addition to security concerns, there are also unresolved copyright issues – Getty Images thinks it’s vague enough to block AI-generated content from its image library. Many creators may also be concerned about their work. If someone can theoretically create any image just by typing a description in the prompt box, why pay a designer or illustrator for it?
For now, though, technology still needs a lot of guidance and someone with decent artistic judgment to get the most out of it. A whole new area of work opens up – Writing AI cues, and there are AI hint markets selling hints for specific styles of images. There is still no API, but the company claims in a blog post that it is testing one.
What is DALLE-2?
DALL · E 2 (the name is a continuation of Pixar’s “Dali” (as in Salvador) and “WALL-E”) is an AI text image generator based on machine learning. Created by the Artificial Intelligence company Open AI, it is a generative tool, which means that users can generate graphics from scratch using text prompts.
Users describe the subject and style of the image they want, and the DALL-E 2 will use its training on millions of existing photos and captions to create what it thinks fit that description. For example, you can type “anthropomorphic hedgehog in a suit and tie, studio lighting, award-winning high definition photography.” Yes, someone did just that – see the results in the tweet below.
The DALL-E 2 can also be used to edit or make variations of an existing work. One of the last features, called repaint, allows users to extend an image beyond its original frame.
ancient Egyptian hieroglyphs depicting a man sitting at a computer with the word Dalle on the screen # dalle2 pic.twitter.com/EBzR8ESZ70September 28, 2022
What can the DALL-E 2 be used for?
The DALL-E 2 can be used to create images in a wide variety of styles by writing text prompts. It can even recreate the styles of famous artists. Brands, including Heinz, have experimented with using it to create marketing and advertising materials, though so far only as an advertising gimmick.
The tool can be useful to speed up background creation for games and other uses, and plastic surgeons and architects use it to imagine what their work could look like, and a German art institute runs a growing AI art exhibition that uses DALL-E 2 to generate graphics based on popular Twitter themes. But it’s mostly used for artistic experimentation and idea generation and testing – check out our rundown of the weirdest AI creations.
OpenAI says: “Over 1.5 million users are currently actively creating over 2 million images a day with DALL-E – from artists and creative directors to authors and architects – and around 100,000 users share their creations and opinions in our Discord community.” .
Can #AI combine the works of Van Gogh, Monet, Munch and Hocusai? @OrbAmsterdam asked this question and challenged @OpenAI. The result is impressive (pun intended) This is how the new skill #outpainting # DALLE2👇🏼pic.twitter.com / WWeyRvea6x worksSeptember 28, 2022
How much is the DALL-E 2?
DALLE-2 was free for the first two months, but in July, OpenAI began charging for the credits that are needed to generate graphics on the platform. All new users get quite a lot of free credits to use but then only 15 free credits each month.
Users will be able to purchase additional credits for $ 15 for 115 credits (enough to generate 460 square images). OpenAI has invited artists who need financial help to apply (opens in a new tab) for subsidized access.