Skip to content
Tech News
← Back to articles

OpenAI releases ChatGPT Images 2.5 with ‘sharper details’ and ‘more precise editing’

2026-09-08 | original
read original get Wacom Intuos Wireless Drawing Tablet → more articles
Why This Matters

OpenAI is iterating quickly on image generation, following April's Images 2 with a 2.5 update that emphasizes image quality, multi-turn editing reliability, and up to 50% lower latency. New consumer features like in-app Sketch input, format templates, and prompt sharing push ChatGPT further into creative-tool territory, while two API model tiers give developers a cheaper-and-faster option and a premium editing-focused one.

Key Takeaways
Worth a Look

Wacom Intuos Wireless Drawing Tablet — With ChatGPT Images 2.5 adding a Sketch tool for drawing reference art right in the chat, a pen tablet makes those rough guides far easier to draw than with a mouse or trackpad. The Wacom Intuos is a compact, pressure-sensitive slate that plugs into your computer and lets you rough out compositions in seconds before handing them to the AI to refine.

See Wacom Intuos Wireless Drawing Tablet on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.

In April, OpenAI released upgraded image generation technology with ChatGPT Images 2. Five months later, the company is releasing an enhanced version, ChatGPT Images 2.5.

ChatGPT Images 2 was a notable leap over the company’s earlier image generation tools.

It added 2K resolution output, multiple aspect ratio support, and the ability to use web research for up-to-date information. Images 2 also added non-Latin language expertise and two intelligence levels: Instant and Thinking.

The latest Images 2.5 version touts “sharper details, faster generation, more precise editing, and better tools for creating and sharing.”

“Images 2.5 produces more natural lighting and richer textures, is better at preserving the subjects in your reference photos, and follows editing instructions more reliably across multiple turns,” OpenAI says.

“We’ve also reduced image generation latency by up to 50% compared with Images 2.0, so you can generate images and refine your concepts more quickly.”

Additionally, the company details a new “Sketch” feature that enables drawing directly in ChatGPT. This can be used as a reference for image generation. Plus OpenAI is introducing templates for popular image formats, prompt sharing for others to try your ideas related to image-gen, and more.

Additionally, OpenAI is releasing two versions of Images 2.5 for developers to build around in their apps. GPT-Image-2.5 Flare and GPT-Image-2.5 Sunburt will be available through OpenAI’s API:

GPT‑Image‑2.5 Flare brings the same improvements in quality, editing, and speed to the API and is the default choice for most applications, delivering higher-quality images than GPT‑Image‑2 at 50% lower latency. It’s well suited to everything from creator and social content to product experiences, visual search, rapid image prototyping, and high-volume generation. GPT‑Image‑2.5 Sunburst is built for premium visual workflows that benefit from tighter control across edits. Use it for creative and editing workflows like production-ready campaign creative or polished product imagery.

“Images 2.5 is rolling out today to ChatGPT, ChatGPT Work, and Codex users across all tiers on desktop, mobile, and web,” according to OpenAI. You can learn more about the new image-gen technology here.

... continue reading

Explore topics: openai chatgpt images 2.5 image generation gpt-image-2.5 openai api
Related:
ChatGPT Images 2.5
The first trailer for the Sam Altman biopic is damn creepy
OpenAI fought dirty on career-making math problem, says NYU mathematician
OpenAI Says It Has Solved a Millennium Prize Problem—a Holy Grail of Math
On the Navier–Stokes Millennium Prize Problem

© 2026 GoKawiil

About | Editorial Policy | Contact