OpenAI Launches ChatGPT Images 2.0 With Thinking Capabilities and Better Text Rendering

OpenAI launched ChatGPT Images 2.0, an upgraded image model with stronger prompt-following and improved visual composition.

The model can generate multiple images, inspect its own output, and use web search for more current context.

It also renders text more accurately across several languages, including non-Latin scripts.

The update expands access across ChatGPT, Codex, and the API, making image generation more useful for complex and multilingual work.