What is DALL·E 3?
DALL·E 3 is a text-to-image generation system that understands significantly more nuance and detail than previous systems, allowing users to easily translate their ideas into exceptionally accurate images.
Features of DALL·E 3
- Available to all ChatGPT users and developers through the API
- Generates images that exactly adhere to the text provided
- Built natively on ChatGPT, allowing for brainstorming and refining of prompts
- Can be used to create images from simple sentences to detailed paragraphs
- Allows for tweaking of generated images with just a few words
How to Use DALL·E 3
DALL·E 3 can be used to generate images from text prompts. Simply provide a prompt, and the system will generate an image that matches the description.
Safety Features of DALL·E 3
- Mitigations to decline requests that ask for violent, adult, or hateful content
- Ability to decline requests that ask for a public figure by name
- Improved safety performance in risk areas like generation of public figures and harmful biases
- Researching ways to help people identify when an image was created with AI
- Experimenting with a provenance classifier to identify generated images
Creative Control and Credits
- Designed to decline requests that ask for an image in the style of a living artist
- Creators can opt their images out from training of future image generation models
- Credits to the core research and execution team, research contributors, inference optimization team, product team, safety team, and communications team.