Although the terms “artificial intelligence” and “machine learning” have been around for many years, to most people who are not interested in these technologies, they are just fancy words. Now people will be able to see for themselves how powerful these technical tools can be, thanks to DALL-E, an OpenAI image generator.

Until now, access to the OpenAI DALL-E image synthesis tool has been limited to an invitation-only system. Today, the platform opened the tool to everyone. This means that anyone can sign up and use it.

DALL-E is a deep learning image synthesis model that has been trained on hundreds of millions of images obtained from the Internet. It uses a technique called latent diffusion to study associations between words and images. As a result, DALL-E users can enter a text description or text hint and see it visually as a 1024 × 1024 pixel image in virtually any art style the user chooses.

In addition to generating images from text signals, DALL-E also includes a feature called “Outpainting” that allows you to load an image and extend its boundaries using image synthesis. You can also combine several photos into one, creating a visual bridge between them.

In April of this year OpenAI premiered DALLE-2, which impressed a test audience of 200 researchers with its ability to create near-photorealistic images and mimic the styles of different artists from different eras and generations. After a gradual opening to more users and a pricing model in July, more than 1.5 million users worldwide are now using DALL-E 2 to create more than 2 million images per day, according to OpenAI.

DALL-E is a commercial service that has some significant limitations. New users get 50 free credits, and you can purchase credits in groups of 115 at $15 each. Registration requires a phone number in addition to other information. Images created with DALL-E are owned by OpenAI, but the company grants users exclusive rights to “play and display” their generations as long as they comply with its content policy.