Back

DALL-E

DALL-E is a series of generative AI models developed by OpenAI that create digital images from natural language descriptions, also known as prompts. The name “DALL-E” is a portmanteau of the artist Salvador Dalí and Pixar’s animated robot WALL-E, reflecting the model’s design to merge artistic creativity with artificial intelligence[1][5].

The first version, DALL-E 1, was introduced on January 5, 2021, and it utilized a discrete variational autoencoder (dVAE) to generate images from text[5][7]. DALL-E 2, which was released in April 2022, improved upon the original by using a diffusion model that can generate higher quality and more photorealistic images[5]. DALL-E 3, the latest iteration as of the knowledge cutoff date, was released on August 10, 2023, and it further enhances the capabilities of the model, including the ability to generate larger images at a faster rate and with more detailed customization options[1][2].

Citations:

[1] https://en.wikipedia.org/wiki/DALL-E

[2] https://openai.com/dall-e-3

[3] https://openai.com/dall-e-2

[4] https://help.openai.com/en/articles/6338764-are-there-any-restrictions-to-how-i-can-use-dall-e-2-is-there-a-content-policy

[5] https://www.techtarget.com/searchenterpriseai/definition/Dall-E

[6] https://openai.com/blog/dall-e-introducing-outpainting

[7] https://openai.com/research/dall-e

[8] https://boostlabs.com/blog/10-limitations-of-visual-outputs-from-dall-e-and-similar-ai-generative-models/

[9] https://www.datacamp.com/blog/what-is-dall-e

[10] https://www.cronj.com/blog/dall-e-2-features-capabilities-and-applications/

[11] https://lablab.ai/apps/tech/openai/dall-e-2