OpenAI is gearing up to roll out the third version of DALL-E, its text-to-image AI system, which reportedly improves its predecessor's capabilities and can generate results within the ChatGPT app. The company demonstrated how the new iteration integrates with ChatGPT to The Verge, and it showed the publication how users can ask the chatbot to write a lengthy and detailed prompt the image AI can use.
OpenAI told Axios that DALL-E 3 is "significantly better" at being able to grasp a user's intention, especially if the prompt is long and detailed. If a user can't articulate what they want in a way that can maximize the image generator's abilities, then ChatGPT can help them write a comprehensive prompt for it. In the demo to The Verge, DALL-E produced four results for a prompt asking for a ramen restaurant logo in the mountains within ChatGPT.
DALL-E 3 was also designed to be better at creating elements its predecessors and other AI generators are having trouble with, such as depictions of hands and texts in images. And it's supposed to have better security measures — the company said it trained the new DALL-E ignore certain words in prompts that could lead to explicit or hateful images.
In addition, OpenAI has implemented measures that could prevent future potential lawsuits. The current version of DALL-E can generate images in the style of living artists, but the next version was designed to decline requests asking it to mimic their work. Artists will also be able to submit work they own through a form on the website and ask for it to be removed.
OpenAI plans to release DALL-E 3 next month to ChatGPT Plus and enterprise customers. The new image generator will then make its way to OpenAI's research labs and API customers sometime this fall, but the company has yet to announce its general public availability.