Dall-E 3 Combines with ChatGPT to Produce Sophisticated Images on Request
As the world adapts to ChatGPT and other AI-driven bots and platforms, it is becoming clear that some professions will benefit more than others from this wave of AI products and uses.
The world of art is one that comes to mind with this article we found on wired.com. The story is about the merging of the abilities of OpenAI’s Dall-E 3 and ChatGPT. By adding the chatbot, a person can speak to their AI assistant in normal conversation and the chatbot will direct the generative AI to make the picture requested.
“What’s new with Dall-E 3 is how it removes some of the complexity required with refining the text that is fed to the program—what’s known as “prompt engineering”—and how it allows users to make refinements through ChatGPT’s conversational interface. The new tool could help lower the bar for generating sophisticated AI artwork, and it could help OpenAI stay ahead of the competition thanks to the superior abilities of its chatbot.”
Getting the prompt right is the most important part of using a generative platform. How you ask for an image will require a little practice to get it exactly right.
Potato King Request
Will Knight is the author of this piece and he gives us this example of the new Dall-E 3 and ChatGPT being asked to work together.
“Take this image of the potato king, for example.
“This kind of quirky AI-generated art has become commonplace on social media thanks to a number of tools that turn a text prompt into a visual composition. But this one was created with a significant amount of artistic assistance from ChatGPT, which took a short prompt and turned it into a more detailed one, including instructions about how to compose it correctly.”
Dall-E and generative AI art rely on an algorithm that’s fed huge quantities of labeled images scraped from the web and other sources. It’s a diffusion model to predict how to render an image for a given prompt. Using a deep database can help produce “complex, coherent, and aesthetically pleasing imagery.” What’s different with Dall-E 3 is the way humans and machines interact.
Dall-E 3 will let users refine a creation through ChatGPT as if they were asking a real artist to make changes.
“You won’t really have to worry about fussing around with really long prompts,” says Aditya Ramesh, lead researcher and head of the Dall-E team. “Instead, you can just interact with ChatGPT as if you were talking to a coworker.”
The next few weeks and months should be filled with fantastical pieces of generated art that would have been impossible just two years ago. Now AI images winning art contests. We live in exciting times.
read more at wired.com