OpenAI introduces ChatGPT Images 2.5
ChatGPT Images 2.5 delivers faster, sharper image generation and precise edits Create natural-looking visuals in ChatGPT and the API with new tools built in
OpenAI has released ChatGPT Images 2.5, a new image model designed to improve detail, editing precision, and generation speed across ChatGPT and the API.
The company says the model produces more natural lighting and richer textures, preserves reference photo subjects more reliably, and handles multistep edits more consistently. OpenAI also says image generation latency is up to 50% lower than Images 2.0.
The update adds new creative tools in ChatGPT, including Sketch for drawing rough ideas directly in the app, templates for common formats such as flyers and product photos, image comments for targeted edits, and prompt sharing. OpenAI says Images 2.5 is available to ChatGPT, ChatGPT Work, and Codex users on desktop, mobile, and web, while two new API models, GPTImage2.5 Flare and GPTImage2.5 Sunburst, are also rolling out.