When a major AI company releases a new image model, it can revive interest and boost usage, especially if social media users adopt the meme-enabled trend, altering images of themselves. Last year, Google’s launch of the Nano Banana model was a major moment for the company, especially after users started posting their surreal sculptures online. Earlier this year, ChatGPT images caused a stir on social media as users shared AI-generated caricatures.
What’s different?
Because the new model can use ChatGPT’s “logic” capabilities, Images 2.0 can search the Internet for recent information and generate more than one image at a time. In short, the bot can use additional steps to output more complete generations from a single prompt. Images 2.0 also has the latest knowledge cutoff date: December 2025.
This also means that the new model has a more detailed output. For example, I created an infographic with San Francisco’s weather forecast for the next day as well as activities to do. The image, produced by ChatGPT, included accurate-looking images of the Ferry Building, Castro Theatre, Painted Ladies House, and Transamerica Pyramid, along with accurate weather details for a rainy day.
Additionally, Images 2.0 is more customizable for users who want unique aspect ratios for image output. The new model can generate images ranging from 3:1 wide to 1:3 tall, and users can adjust the image size as the AI tool prompts.
first impressions
After a few hours of drawing with the new model, I was generally impressed with the text rendering capabilities, at least in English. Not long ago, image output showing text from any major model often included many garbled letters or words with erroneous extra letters. ChatGPT struggled to accurately label images two years ago, so the cleaner, more complex output from Images 2.0 is a sign of continued improvement. Google has also focused on improving image output featuring text in its recent iterations of the Nano Banana.
<a href