OpenAImodelChatGPT Images 2.5
OpenAI's new image model in ChatGPT, with faster generation and edits that change only the part you point at.
Details
- Generates images up to 50% faster than Images 2.0
- Holds subjects from your reference photos steady across repeated edits, so a product or a face does not drift between versions
- You can leave a comment on one part of a generated image and it changes only that part
- Follows editing instructions more reliably across several turns of the same conversation
- Rolling out to all ChatGPT, ChatGPT Work, and Codex users on every tier, on desktop, mobile, and web
Best for
Producing and revising campaign visuals inside ChatGPT instead of round-tripping through a design tool.
When to use it
You need several versions of the same image and the subject has to stay recognizable across all of them.
Who benefits
Content and brand marketers who make their own social and ad creative.
Join the newsletter to get ahead with AI.
I share strategies, new modules, free guides, and tools to get you better at using AI in your work.
Leading a team? See team programs →