Honestly? It looks more promising than Bing Image Creator, at least in the presented demo.
“DALL-E 3 is built natively on ChatGPT, which lets you use ChatGPT as a brainstorming partner and refiner of your prompts. Just ask ChatGPT what you want to see in anything from a simple sentence to a detailed paragraph,” says OpenAI in a blog post.
But, what makes DALL-E 3 stand out from its predecessor, DALL-E 2, you may ask?
Well, DALL-E 3 is better than DALL-E 2 because it can follow complex instructions and generate images that accurately represent scenes with specific objects and the relationships between them.
In a lengthy X (fka Twitter) thread, OpenAI demonstrates some of the artworks that DALL-E 3 could perform. Here, you’re looking at a glass heart rests on a pedestal in the middle of a sea with the words “Find the universe within you” are inscribed in bold letters across the horizon.
“An illustration of a human heart made of translucent glass, standing on a pedestal amidst a stormy sea. Rays of sunlight pierce the clouds, illuminating the heart, revealing a tiny universe within. The quote ‘Find the universe within you’ is etched in bold letters across the… pic.twitter.com/S3cKMkG67T
— OpenAI (@OpenAI) September 20, 2023
ChatGPT Plus and Enterprise customers will be able to use DALL-E 3 in early October. As with DALL-E 2, you own the images you create with DALL-E 3 and can use them however you like, including reprinting, selling, and merchandising them, although you cannot request images for a public figure by name, like celebrities.
OpenAI is also working on a provenance classifier, an internal tool that lets you identify AI-generated images.
“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,” the announcement reads.