Urgent.News

What's breaking now, across thousands of outlets.

AI

Google web traffic is 'steady,' while ChatGPT, Gemini see gains: BofA

In April, OpenAI unveiled upgraded image generation technology through ChatGPT Images 2. Now, five months later, the company has released an enhanced version, ChatGPT Images 2.5. This latest iteration surpasses its predecessor by delivering "sharper details, faster generation, more precise editing, and better tools for creating and sharing," according to OpenAI.

Images 2.5 boasts improved lighting and textures, maintains subjects from reference photos more accurately, and adheres to editing instructions more reliably in successive turns. Moreover, OpenAI reports a reduction in image generation latency by up to 50% compared to Images 2.0, allowing users to generate images and refine concepts more swiftly.

The company has also introduced a "Sketch" feature, enabling users to draw directly in ChatGPT as a reference for image generation. Additionally, OpenAI is rolling out templates for popular image formats, prompt sharing for others to try out ideas related to image generation, and more.

OpenAI is offering two versions of Images 2.5 for developers to build upon in their applications. GPT-Image-2.5 Flare and GPT-Image-2.5 Sunburst will be available through OpenAI's API. GPT-Image-2.5 Flare, the default choice for most applications, boasts the same quality, editing, and speed improvements as Images 2.5, while achieving 50% lower latency, making it ideal for creator and social content, product experiences, visual search, rapid image prototyping, and high-volume generation.

In contrast, GPT-Image-2.5 Sunburst is designed for premium visual workflows that demand tighter control over edits. It suits creative and editing workflows, such as production-ready campaign creative or polished product imagery.

Today's ChatGPT Images 2.5 release coincides with the launch of GPT-6 Astra. Across all tiers on desktop, mobile, and web, ChatGPT, ChatGPT Work, and Codex users can access this new image generation technology. Further details about Images 2.5 can be found here.

Written by urgent.news from 9to5Mac's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

This story

This is one outlet's version. Read the fullest account.

Read the original at seekingalpha.com →

More in AI

LongHorizon-Harness: The Loop Engineering That Lets Agents Run for Hours, Not Minutes

Every agent user hits the same wall: it can't go the distance. Give an agent a complex, multi-app task, and somewhere along the way it loses the plot — the context window fills up and it forgets its…

  • LongHorizon-Harness addresses agent limitations in completing multi-step tasks.
  • Core functionality includes Plan → act → verify → checkpoint or recover loop.
  • Project validated by arXiv paper and benchmarks on WeaveBench, OSWorld 2.0, Terminal-Bench 2.1.

More from Tuesday 8 September →