DALL·E 3 has made significant strides in comprehending intricate details and nuances compared to its predecessors. This breakthrough technology empowers you to effortlessly transform your thoughts into remarkably precise visual representations.
4x greater resolution than DALL·E 2
A new version of OpenAI’s text-to-image model that can generate realistic and accurate images from complex prompts.
- Creative control
Users can opt their images out from training of future image generation models, and have full ownership and rights to use the images they create with DALL·E 3.
- Safety measures:
DALL·E 3 has mitigations to prevent harmful or unethical generations, such as violent, adult, or hateful content, images of living artists or public figures, and propaganda or misinformation.
- ChatGPT integration
DALL·E 3 is built natively on ChatGPT, which allows users to use ChatGPT as a brainstorming partner and refiner of their prompts, and to make tweaks to the generated images with natural language.
- Provenance classifier:
A new internal tool that can help OpenAI identify whether or not an image was generated by DALL-E 3. This tool is intended to help OpenAI better understand the ways generated images might be used and to research the best ways to help people identify when an image was created with AI.
- Release schedule:
DALL-E 3 is now in research preview, and will be available to ChatGPT Plus and Enterprise customers in October, via the API and in Labs later this fall. OpenAI plans to stagger the release of DALL-E 3 but did not commit to when a free public version will be released.