Chatbots were originally designed to chat. But they can generate images, too.
On Tuesday, OpenAI beefed up its ChatGPT chatbot with new technology designed to generate images from detailed, complex and unusual instructions.
For instance, if you describe a four-panel comic strip, including the characters who appear in each panel and what they are saying to one another, the technology can instantly generate an elaborate cartoon.
Though previous versions of ChatGPT could generate images, they could not reliably create images by blending such a wide array of concepts.
The new version of ChatGPT is indicative of a wider change in artificial intelligence technology. After beginning as systems that merely generated text, chatbots are morphing into tools that combine chatting with various other abilities.
The technology that underpins the new version of ChatGPT — called GPT 4-o — also allows the chatbot to receive and respond to voice commands, images and videos. It can even speak.
Released at the end of 2022, the original ChatGPT learned its skills by analyzing enormous amounts of text from across the internet. It learned to answer questions, write poetry and generate computer code.
It could not generate images. But about a year later, OpenAI released a new version of ChatGPT that could generate images, called DALL-E. But ChatGPT and DALL-E were separate systems.
Now, OpenAI has built a single system that learns a wide range of skills from both text and images. In generating its own images, this system can draw on everything ChatGPT has learned from the internet.
“This is a completely new kind of technology under the hood,” said Gabriel Goh, an OpenAI researcher. “We don’t break up image generation and text generation. We want it all to be done together.”
Traditionally, A.I. image generators have struggled to create images that were markedly different from any existing image. If you asked an image generator to create an image of bicycle with triangular wheels, for instance, it struggled.
Mr. Goh said the new ChatGPT could handle this kind of request.
OpenAI said that, beginning Tuesday, this new version of ChatGPT would be available to people using both the free and paid versions of the chatbot. This includes both ChatGPT Plus, a $20-a-month service, and ChatGPT Pro, a $200-a-month service that provides access to all of the company’s latest tools.
(The New York Times sued OpenAI and its partner, Microsoft, in December for copyright infringement of news content related to A.I. systems.)
