ChatGPT Images 2.5 brings faster generation and more precise editing

OpenAI has released ChatGPT Images 2.5, its latest image generation and editing model for ChatGPT and the API.

The model is designed to improve both image quality and editing reliability. OpenAI says Images 2.5 produces more natural lighting, richer textures and stronger subject fidelity when working from reference photos.

One of the biggest changes is editing consistency.

The model is better at changing only the requested part of an image while leaving subjects, composition and other details intact. It is also designed to preserve previous edits more reliably during longer multi-turn editing sessions.

OpenAI says generation latency has been reduced by up to 50% compared with Images 2.0.

ChatGPT is also gaining new creation tools around the model. Sketch lets users draw a rough visual reference directly in ChatGPT, while templates provide starting structures for formats such as posters, merchandise and product photography. Users can also place comments directly on images to request targeted changes.

OpenAI says more than 3 billion images are now created every week across ChatGPT Images and GPT-Image models in the API.

Developers are getting two new API models.

GPT-Image-2.5 Flare is positioned as the default model for most image workflows, while GPT-Image-2.5 Sunburst is aimed at higher-precision creative and editing tasks where longer generation time is acceptable.

Images 2.5 is rolling out across ChatGPT, ChatGPT Work and Codex on desktop, mobile and web.

For creative teams, the most important improvement may not be raw image quality. Reliable editing and reference preservation make generated images considerably more useful inside repeatable production workflows.