88Z AI, 9 September — OpenAI has released ChatGPT Images 2.5, significantly improving detail, editing precision, and speed, with a 50% reduction in latency. New features like sketches and templates are now available, along with two new API models, Flare and Sunburst.
At a glance
- ChatGPT Images 2.5 reduces generation latency by 50%, improving editing consistency and detail
- Platform adds hand-drawn sketch features, while API launches Flare and Sunburst models
The update
OpenAI has officially launched the next-generation image generation model, ChatGPT Images 2.5. This model achieves comprehensive upgrades in image detail rendering, editing precision, and generation speed. Compared to version 2.0, generation latency is reduced by 50%, allowing for more accurate retention of subject features from reference photos and maintaining consistency across multiple rounds of editing. Alongside the model update, the ChatGPT platform has simultaneously introduced several creative assistance features, including hand-drawn sketch generation, template usage, image comments, and prompt sharing. Additionally, OpenAI has launched two new models, Flare and Sunburst, via its API, providing developers with more options.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- OpenAISource published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.