OpenAI’s updated image generator can now pull information from the web
The Verge • • general
Key Points:
- OpenAI has launched ChatGPT Images 2.0, an upgraded AI image generator with enhanced "thinking capabilities" that allow it to search the web and create multiple images from a single prompt.
- Powered by the new GPT Image 2 model, the tool can now follow instructions more precisely, preserve specific details, generate text in images, and pull information from the web for improved image reasoning.
- Subscribers to ChatGPT Plus, Pro, Business, and Enterprise can generate up to eight images at once with consistent characters, objects, and styles, facilitating projects like manga pages or design plans.
- The update supports higher resolution images up to 2K, a wider range of aspect ratios, and improved text generation in multiple languages including Japanese, Korean, Chinese, Hindi, and Bengali.
- ChatGPT Images 2.0 is available immediately to all ChatGPT and Codex users, amid increasing competition from tools like Google’s Nano Banana Pro and Microsoft’s MAI-Image-2.
