OpenAI has unveiled the third iteration of its generative AI visual art platform, Dall-E.
This upgraded version introduces several enhancements, including the ability for users to employ ChatGPT to formulate prompts and an expanded array of safety options.
Dall-E's primary function is the transformation of text prompts into corresponding images. While Dll-E 2 occasionally misconstrued specific phrasing, the latest iteration showcases significant improvements in contextual comprehension, as elucidated by OpenAI researchers.
One notable addition to Dall-E 3 is its integration with ChatGPT. This feature enables users to bypass the need to devise intricate prompts for Dall-E 3 independently. Instead, they can simply enlist ChatGPT's assistance to generate a prompt. The chatbot can craft a paragraph (preferably longer sentences for optimal Dall-E performance) for Dall-E 3 to follow. Of course, users who possess specific ideas for Dall-E can still furnish their own prompts.
Dall-E made its initial debut in January 2021. By the time Dall-E 2 was introduced in 2022, OpenAI had taken steps to address concerns over the platform's content.
They initiated a waitlist system to carefully control access, as Dall-E had faced criticism for generating photorealistic explicit imagery and exhibiting biases in photo generation.
In September of the previous year, OpenAI removed the waitlist and made DALL-E 2 accessible to the general public.
The latest iteration of Dall-E will have a phased-release strategy. Initially, it will be available to ChatGPT Plus and ChatGPT Enterprise users in October, with subsequent availability to research labs and its API service in the autumn season.
While OpenAI intends to release Dall-E 3 incrementally, they have not yet committed to a specific timeline for the launch of a free public version.