DALL-E 2 is a new AI system that can create realistic images and art from a description in natural language.

In the coming weeks OpenAI will invite a million people from its waitlist to create images from text using the DALL-E 2 AI system. Users can create with DALL·E using free credits that refill every month, and buy additional credits in 115-generation increments for $15. (OpenAI)

How it works

In this first phase of the beta, users can buy additional DALL·E credits in 115-credit increments (460 images) for $15 on top of their free monthly credits.

One credit is applied each time a prompt is entered and a user hits “generate” or “variations.”

Users would be allowed to use commercially the images they create with DALL-E 2. They have the right to reprint, sell, and merchandise the images for commercial projects including:

• illustrations for children’s books
• art for newsletters
• concept art and characters for games
• moodboards for design consulting
• storyboards for movies

“We’ve seen much more interest than we had anticipated, much bigger than it was for GPT-3,” said Peter Welinder, vice president of product and partnerships at OpenAI, to MIT Technology Review.

OpenAI is building in some safeguards, however, against explicit and violent content, images that are deceptively similar to public figures, and bias relating to race or gender.

Related Story: OpenAI’s DALL-E 2 Program Draws (And Edits) Images From Text Commands