OpenAI Beefs Up ChatGPT’s Image Generation Model
SMRTR summary
OpenAI launched ChatGPT Images 2.0, an upgraded image generation model that can create multiple images from a single prompt, render accurate text in English, and access real-time internet information. It supports wider aspect ratios and a December 2025 knowledge cutoff. However, early testing showed the model still struggles with accurate text rendering in non-English languages like Chinese, suggesting room for improvement globally.
SMRTR provides this summary for quick context. The original article belongs to Wired.
Read the original article