DALL-E[2] is an artificial intelligence[1] (AI) model developed by OpenAI[3], first announced in January 2021. It is based on a modified version of the GPT-3[4] model and is designed to generate images from text descriptions. DALL-E has the ability to create a range of images in various styles, including photorealistic images, paintings, and even emojis. It can understand and manipulate design elements, creatively add details to prompts, and understand visual trends. However, DALL-E also has its limitations, such as difficulty understanding language and potential biases due to its reliance on public datasets. It has sparked debates about AI’s role in art and creativity, with its potential impact on artists and the broader creative industry. Despite these debates, DALL-E has generally been well-received, with significant excitement about its potential applications and impact on the future of visual art.
DALL·E, DALL·E 2, and DALL·E 3 are text-to-image models developed by OpenAI using deep learning methodologies to generate digital images from natural language descriptions, called "prompts."
Developer(s) | OpenAI |
---|---|
Initial release | January 5, 2021 |
Stable release | DALL·E 3
/ August 10, 2023 |
Type | Text-to-image model |
Website | labs |
The first version of DALL-E was announced in January 2021. In the following year, its successor DALL-E 2 was released. DALL·E 3 was released natively into ChatGPT for ChatGPT Plus and ChatGPT Enterprise customers in October 2023, with availability via OpenAI's API and "Labs" platform provided in early November. Microsoft implemented the model in Bing's Image Creator tool and plans to implement it into their Designer app.