OpenAI has announced the latest version of its text-to-image generation model DALL-E 3 with the new integration with ChatGPT. OpenAI noted that the integration with ChatGPT will allow users to ‘craft amazing prompts’ and bring their ideas to life.
In a statement about their latest generative AI-based offering, OpenAI said, “Our new text-to-image model, DALL·E 3, can translate nuanced requests into extremely detailed and accurate images.”
“Modern text-to-image systems have a tendency to ignore words or descriptions, forcing users to learn prompt engineering. DALL·E 3 represents a leap forward in our ability to generate images that exactly adhere to the text you provide.” OpenAI added.
The Sam Altman-led company promises that DALL-E 3 will deliver 'significant improvements' over DALL-E 2 even with the same text prompt. Moreover, similar to DALL-E 2, users do not need to take OpenAI's permission for reprinting selling or merchandizing the images created using DALL-E 3.
When will DALL-E 3 be available?
DALL-3 is currently in research preview and will be made available to ChatGPT Plus and Enterprise users in October this year followed by API and Labs customers later in the year. OpenAI did not announce when the latest text-to-image generating tool will be available to free customers.
What has changed in DALL-E 3?
OpenAI says it has improved safeguards in areas like generation of images of public figures, carrying out propaganda or misinformation and the ability to generate violent, adult, or hateful content.
Moreover, DALL-E 3 has been designed to decline requests by users for generating images in the style of a living artist while creators can also opt their images out of the training of future image generation models.
