The DALL-E image generator is now open to everyone

Enlarge / A work created with OpenAI's DALL-E image generator. Open AI

If you've been itching to try OpenAI's Image Synthesis tool but have been blocked by the lack of an invite, now's your chance. Today, OpenAI announced the removal of the waitlist for its DALL-E AI image generator service. This means that anyone can register and use it.

DALL-E is a deep learning image synthesis model that has been trained on hundreds of millions of images retrieved from the internet. It uses a technique called latent diffusion to learn associations between words and pictures. Therefore, DALL-E users can enter a textual description, called a prompt, and see it rendered visually as a 1024 x 1024 pixel image in almost any art style.

Besides image-to-text generation, DALL-E also includes a feature called "Outpainting" which allows you to upload an image and extend its borders using image synthesis. You can also merge several photos into one by generating a visual bridge between them, mixing styles.

Enlarge / A DALL-E example of "An astronaut on horseback". Open AI

OpenAI announced an earlier version of DALL-E in January 2021 with surprising capabilities but obvious limitations. In April this year, he created DALLE-2, which wowed a limited test audience of 200 researchers with its ability to generate near-photorealistic images and mimic artists' styles. After gradually opening up to more users and implementing a pricing model in July, more than 1.5 million users worldwide are now using DALL-E (renamed DALL-E 2) to create more than 2 million images per day, according to OpenAI.

DALL-E is a commercial service, and it has important limitations. New users get 50 free credits, and you can buy credits in groups of 115 for $15 each. Images generated with DALL-E are the property of OpenAI, but the company grants users exclusive rights to "reproduce and display" their builds as long as they comply with the content policy. Content violations will void your right to legally use generated images.

Previously, we talked a lot about Stable Diffusion, which is an open source (and competitor) image model similar to DALL-E created by Stability AI. For a month, Stable Diffusion has been available with some restrictions through open source channels and its own commercial website. Now that DALL-E is open to everyone, the competition between computer-generated imagery models is likely to intensify.