Back to AI updates
OpenAINew features

ChatGPT Images 2.0 in ChatGPT

Useful if you create visuals for presentations, marketing or training materials — describe the image you want in plain language, and on paid plans a new "thinking" step now interprets your request more carefully before generating, so first attempts should match what you actually asked for more often.

Read the original source 1 min read

What changed

A new image generation model launched across all plans, adding a "thinking" capability for paid users to improve prompt understanding and output quality.

Why it matters to your work

Useful if you create visuals for presentations, marketing or training materials — describe the image you want in plain language, and on paid plans a new "thinking" step now interprets your request more carefully before generating, so first attempts should match what you actually asked for more often.

What to try next

Next time you need a visual for a presentation or training material, describe it in plain language in ChatGPT Images; on a paid plan, the new thinking step should get closer on the first attempt.

Source & availability

This is a summary of a published provider announcement, with practical context from SCALA’s feed.

Plan, region, workspace and rollout conditions may affect access in Australia. Check the original source for current availability.

help.openai.com