In April, OpenAI introduced upgraded image generation capabilities through ChatGPT Images 2. Five months after that release, the company has now launched an enhanced iteration called ChatGPT Images 2.5.
ChatGPT Images 2 represented a significant advancement beyond the company’s previous image creation systems. This version included 2K-resolution outputs, support for various aspect ratios, and integration with web research for current information. It also brought multilingual proficiency and two distinct intelligence modes: Instant and Thinking.
The latest Images 2.5 highlights sharper details, accelerated generation speeds, improved editing capabilities, and enhanced utilities for content creation and distribution. According to OpenAI, Images 2.5 delivers more realistic lighting and deeper textures, maintains subject integrity from reference images, and adheres to multi-turn editing directives with greater consistency. Furthermore, image generation latency has been cut by up to half compared to Images 2.0, enabling quicker concept refinement.
Additionally, a new Sketch capability allows direct sketching within ChatGPT for reference during image creation. The platform also offers format templates, collaborative prompt sharing, and additional features. Moreover, OpenAI provides two developer-focused variants of Images 2.5 for app integration: GPT-Image-2.5 Flare and GPT-Image-2.5 Sunburst, accessible via the OpenAI API:
GPT-Image-2.5 Flare incorporates identical enhancements in quality, editing, and performance, making it the preferred option for many applications; it outperforms GPT-Image-2 by 50% in latency while serving diverse needs such as creator content, product visualization, visual search, quick prototyping, and large-scale generation.
GPT-Image-2.5 Sunburst targets professional visual projects requiring granular edit control, ideal for producing campaign-ready creatives or high-end product photography.
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 becomes available today for ChatGPT, ChatGPT Work, and Codex users across desktop, mobile, and web,’ reports OpenAI. Further details on this image generation technology are available online.
This release of ChatGPT Images 2.5 comes following the recent GPT-6 Astra announcement.
Do more with your Apple products
Apple AirTag 2 | Add Find My tracking to keys, bags, bikes, more
AirPods 4 | Apple’s newest wireless headphones
AirPods Pro 3 | Apple’s best wireless headphones