OpenAI releases ChatGPT Images 2.5 with faster generation and more precise editing

OpenAI has released ChatGPT Images 2.5, an upgraded image-generation model that produces sharper detail, more natural lighting and richer textures. OpenAI says it also follows editing instructions more reliably across multiple turns and cuts generation latency by up to 50% compared with Images 2.0.

ChatGPT Images 2.5 adds more control

The update is available to ChatGPT, ChatGPT Work and Codex users across all tiers on desktop, mobile and web, according to OpenAI’s announcement.

The model is better at preserving subjects from reference photos while changing the setting, style or composition. It can also make focused edits without changing surrounding details, which should be useful for product imagery, campaign work and other assets that need several rounds of revision.

Sketch and the new API models

OpenAI has added Sketch, which lets users draw directly in ChatGPT and use the result as a visual guide. Templates for formats such as posters and merchandise are also available, while shared images can include the prompt used to create them.

Developers get two API models: GPT-Image-2.5 Flare, the default option for most applications, and GPT-Image-2.5 Sunburst, aimed at workflows that need tighter control across edits. OpenAI says Flare delivers higher-quality images than GPT-Image-2 at up to 50% lower latency, while Sunburst takes longer when more precision is needed.

For UAE users, OpenAI’s announcement does not list a separate local price or rollout restriction. The update is described as available across all ChatGPT tiers, with API pricing listed separately by OpenAI.