DALL-E is a large language model (LLM) developed by OpenAI that can generate images from text descriptions. It was first announced in January 2021 and is still under development. OpenAI is a non-profit research company founded in 2015 by Elon Musk, Sam Altman, Ilya Sutskever, and others.
What does DALL-E do?
DALL-E can generate images from text descriptions. For example, you could give it this text prompt:
3D render of a cute tropical fish in an aquarium on a dark blue background, digital art.
And this is an image generated with the prompt (you can copy and try out):
DALL-E has a number of notable features, including:
- It can generate high-quality images from text descriptions.
- It can generate images of a wide variety of objects and scenes.
- It can be used to create realistic portraits, landscapes, and objects.
- It is still under development, but it has already been used to generate a wide variety of images.
DALL-E’s main competitors are other LLMs that can generate images from text descriptions, such as Midjourney, Stable Duffision.
You need to buy “credits” to use DALL-E. As of this writing you can purchase 115 credits for $15. You can use “credits” to generate images through a text prompt, or make an edit/variation request. Credits are deducted only for requests that return generations; they won’t be deducted for warnings or error messages.
DALL-E has been praised by critics for its ability to generate high-quality images from text descriptions. However, some critics have raised concerns about the potential for DALL-E to be used to generate harmful or misleading images.
[ait-desc] Generates images from text prompts