OpenAI has officially introduced the ChatGPT Images 2.5, its latest image generation model. It brings improved quality, faster generation and more precise image editing tools. The AI giant claims that the new model offers sharper details, more natural lighting and richer textures while improving its ability to preserve people and subjects from reference images.
The company also says that the users can now create over 3 billion images every week across ChatGPT Images and its GPT-Image models available through the API. The company also claims that Images 2.5 can reduce image-generation latency by up to 50 percent compared to Images 2.0. The model is also designed to better understand complex instructions and produce results that more closely match the user’s requested composition and visual style.
ChatGPT Images 2.5 improves targeted editing, allowing users to change specific parts of an image while preserving the rest. For instance, users can modify an object, background or text without changing the main subject or overall composition.
OpenAI has also worked on improving multi-turn editing. The changes that are made during earlier prompts are said to remain more consistent as users continue editing an image. The company says this should help prevent image quality and details from changing unexpectedly during longer creative sessions. However, it does seem to be working.
Also read: Apple event 2026: Date, India timings, expected iPhones and how to watch live
ChatGPT Images 2.5—faster, sharper, smarter, with better tools for creating whatever you can dream of.
— OpenAI (@OpenAI) September 8, 2026
– Faster image generation to keep your ideas flowing
– Improved fidelity for more natural, recognizable images
– Consistent details across multiple edits
– Comment-based… pic.twitter.com/SjHITKJUSV
Along with the new model, OpenAI has also introduced additional image creation tools in ChatGPT. The new Sketch feature lets users draw directly inside ChatGPT and use the drawing as a visual reference. Users can create a rough layout or doodle and combine it with a text prompt to generate a finished image.
The company is also adding Templates for popular formats such as posters, flyers, merchandise and product photographs. Users can select a format and customise it with their own details instead of starting with a blank prompt.
Other additions include the ability to place comments directly on images for more focused edits and share prompts with other users.
ChatGPT Images 2.5 is available across ChatGPT, ChatGPT Work and Codex on desktop, mobile and web. Developers can also access GPT-Image-2.5 Flare and GPT-Image-2.5 Sunburst through the API.