OpenAI revolutionized the tech industry with its innovative AI chatbot, ChatGPT. Running on GPT-3.5, the AI tool sent millions of people into a kind of frenzy, and people started experimenting with the chatbot. A couple of months later, we saw Microsoft introduce its own artificial intelligence tool, the new Bing AI. And Bing AI could do what ChatGPT can’t: generate images from text messages.
Powered by OpenAI’s Dall-E, Bing AI is used today by people around the world to generate AI images. Now, Dall-E has been around since November 2021. And in 2022, it became more powerful with the release of Dall-E 2.
Recently, OpenAI introduced Dall-E 3, which is even more powerful than its predecessor and can generate finer images from text messages. And what is more? You don’t even have to be that good at typing prompts because Dall-E 3 has integrated with ChatGPT, and the AI chatbot will write the directions for you.
OpenAI announces Dall-E 3
Until now, writing the correct and detailed message to generate an AI image was considered a skill. However, with the arrival of Dall.E 3, all you have to do is describe what you want the image to be about, and ChatGPT and Dall-E will take care of the rest. OpenAI, on its website, said that since Dall-E 3 is based on ChatGPT, users can rely on the AI chatbot to make their directions better and more detailed.
“Just ask ChatGPT what you want to see in anything from a simple sentence to a detailed paragraph,” the company says. Introducing Dall-E 3 and sharing how it is more promising than its predecessors, OpenAI says on its website, “DALL·E 3 understands significantly more nuance and detail than our previous systems, allowing you to easily translate your ideas into exceptionally accurate images.”
OpenAI also says that some text-to-image generation systems might ignore certain words or descriptions, which ‘forces users to learn prompt engineering’. But with Dall-E 3, this won’t be required as it “represents a leap forward in our (OpenAI’s) ability to generate images that exactly adhere to the text you provide.”
OpenAI also says that some text-to-image generation systems may ignore certain words or descriptions, which “forces users to learn quick engineering.” But with Dall-E 3, this won’t be necessary as it “represents a leap forward in our (OpenAI’s) ability to generate images that adhere exactly to the text you provide.” In other words, OpenAI claims that people no longer have to learn quick engineering to create great images using AI.
Availability and launch of the free version
Dall-E 3 will be available for the first time to ChatGPT Plus and ChatGPT Enterprise subscribers. Both are paid versions of ChatGPT, running on the latest and most powerful GPT-4 llm.
For ChatGPT Plus and ChatGPT Enterprise users, Dall-E 3 will be available next month. After this, an API service will be implemented. When it comes to a free public version, a report from The Verge claims that OpenAI didn’t really comment on it.