Physical Address
304 North Cardinal St.
Dorchester Center, MA 02124
OpenAI launched a A new AI model for image generation was released Tuesday, dubbed ChatGPT Images 2.0. This model can generate more than one image from a single prompt, such as an entire study booklet, as well as text output, including non-English languages such as Chinese and Hindi. This version is available globally for ChatGPT and Codex Alimentarius users, with a more powerful version available for paying subscribers.
When any major AI company releases a new photo template, it can revive interest and boost usage, especially if social media users adopt a meme-able trend, transforming photos of themselves. Last year, Google’s launch of the Nano Banana model was a big moment for the company, especially when users started posting Very realistic statues themselves online. Earlier this year, ChatGPT images created a buzz on social media as users shared it Cartoons created by artificial intelligence.
What’s different?
Since the new model can take advantage of ChatGPT’s “inference” capabilities, Images 2.0 can search the Internet for up-to-date information and create more than one image at a time. Essentially, the bot can use additional steps to output more extensive generations from a single router. Images 2.0 also has a newer cut-off date: December 2025.
This also means that the new model’s output is more detailed. For example, I created an infographic that includes the San Francisco weather forecast for the next day, as well as activities worth doing. The image created by ChatGPT included precise weather details for the rainy day, along with accurate-looking drawings of the Ferry Building, Castro Theater, painted ladies’ houses, and the Transamerica Pyramid.
Additionally, Images 2.0 is more customizable for users who want unique aspect ratios for image output. The new model can create images ranging from 3:1 wide to 1:3 tall, and users can adjust the image size as part of their prompting of the AI tool.
First impressions
After a few hours of creating images with the new model, I was generally impressed with the text display capabilities, in English at least. Not long ago, image output containing text, of any of the major models, would often include many distorted characters or words with additional misspelled characters. ChatGPT He struggled to name Images are accurate to two years ago, so the cleaner, more sophisticated output from Images 2.0 is a sign of continued improvement. Google has also focused on improving image output that contains text in its images Recent iterations Nano banana.
