"Thinking" image generation model "ChatGPT Images 2.0" — manga, realism, Japanese

OpenAI has launched ChatGPT Images 2.0, a new image generation model for more accurate and natural results.

It improves prompt following, text rendering, multilingual support, and overall composition.

The thinking feature can use web search, generate multiple options, and self-check results.

It is available in ChatGPT, Codex, and the API, making it useful for ads, docs, comics, and UI mockups.