Skip to main content

DALL·E 2

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

Try DALL·E(opens in a new window)Follow on Instagram(opens in a new window)

Latest updates

View all updates
Product
Nov 3, 2022

DALL·E API now available in public beta

"An astronaut launching through space in a colorful explosion", generated by DALL·E 2
Community
Jul 14, 2022

DALL·E 2: Extending creativity

A colorful silhouette of a woman with long, flowing hair, generated by DALL·E 2
Product
Sep 28, 2022

DALL·E now available without waitlist

An oil painting of the side profile of a woman surrounded by flowers, generated by DALL·E 2

DALL·E 2 can create original, realistic images and art from a text description. It can combine concepts, attributes, and styles.

Input
A photorealistic image of an astronaut riding a horse
An astronaut in a spacesuit riding a white horse through a starry space background, creating a surreal scene where the horse appears to be galloping in outer space.
An astronaut in a spacesuit riding a white horse across a reddish, barren landscape, resembling a Martian terrain with a dark sky in the background.
A close-up view of an astronaut in a spacesuit riding a white horse against a pitch-black background, highlighting the astronaut and horse in a dramatic and isolated scene.
An astronaut in a white spacesuit and helmet is riding a white horse across a barren, rocky landscape. The background features a star-filled sky with a large, bright galaxy or nebula, creating a surreal and imaginative scene.
An astronaut in a spacesuit riding a white horse up a rocky hill under a night sky filled with stars, with a shooting star visible in the distance, creating a sense of motion and adventure.

DALL·E 2 can create original, realistic images and art from a text description. It can combine concepts, attributes, and styles.

In January 2021, OpenAI introduced DALL·E. One year later, our newest system, DALL·E 2, generates more realistic and accurate images with 4x greater resolution.
A blurry image of a fox in tall grass.
A digital painting of a fox in a grassy field.

DALL·E 2 is preferred over DALL·E 1 when evaluators compared each model.

  • 71.7%

    preferred for caption matching

  • 88.8%

    preferred for photorealism

A focus on safety

DALL·E 2 began as a research project and is now available in beta. Safety mitigations we have developed and continue to improve upon include:

Preventing harmful generations
We’ve limited the ability for DALL·E 2 to generate violent, hate, or adult images. By removing the most explicit content from the training data, we minimized DALL·E 2’s exposure to these concepts. We also used advanced techniques to prevent photorealistic generations of real individuals’ faces, including those of public figures.
Read about improving safety

Curbing misuse
Our content policy does not allow users to generate violent, adult, or political content, among other categories. We won’t generate images if our filters identify text prompts and image uploads that may violate our policies. We also have automated and human monitoring systems to guard against misuse.
Read content policy(opens in a new window)

Phased deployment based on learning
Learning from real-world use is an important part of developing and deploying AI responsibly. We began by previewing DALL·E 2 to a limited number of trusted users. As we learned more about the technology’s capabilities and limitations, and gained confidence in our safety systems, we slowly added more users and made DALL·E available in beta in July 2022.
View risks and limitations(opens in a new window)

Our hope is that DALL·E 2 will empower people to express themselves creatively. DALL·E 2 also helps us understand how advanced AI systems see and understand our world, which is critical to our mission of creating AI that benefits humanity.

Credits

Research Advancements

Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, Mark Chen

Engineering, Design, Product, and Prototyping

Jeff Belgum, Dave Cummings, Jonathan Gordon, Chris Hallacy, Shawn Jain, Joanne Jang, Fraser Kelton, Vishal Kuo, Joel Lehman, Rachel Lim, Bianca Martin, Evan Morikawa, Rajeev Nayak, Glenn Powell, Krijn Rijshouwer, David Schnurr, Maddie Simens, Kenneth Stanley, Felipe Such, Chelsea Voss, Justin Jay Wang

Comms, Policy, Legal, Ops, Safety, and Security

Steven Adler, Lama Ahmad, Miles Brundage, Kevin Button, Che Chang, Fotis Chantzis, Derek Chen, Frances Choi, Steve Dowling, Elie Georges, Shino Jomoto, Aris Konstantinidis, Gretchen Krueger, Andrew Mayne, Pamela Mishkin, Bob Rotsted, Natalie Summers, Dave Willner, Hannah Wong

Acknowledgments

Thanks to those who helped with and provided feedback on this release: Sandhini Agarwal, Sam Altman, Chester Cho, Peter Hoeschele, Jacob Jackson, Jong Wook Kim, Matt Knight, Jason Kwon, Anna Makanju, Katie Mayer, Bob McGrew, Luke Miller, Mira Murati, Adam Nace, Hyeonwoo Noh, Cullen O’Keefe, Long Ouyang, Michael Petrov, Henrique Ponde de Oliveira Pinto, Alec Radford, Girish Sastry, Pranav Shyam, Aravind Srinivas, Ilya Sutskever, Preston Tuggle, Arun Vijayvergiya, Peter Welinder

Start creating images with DALL·E.

Try DALL·E(opens in a new window)