OpenAI launches ChatGPT Images 2.5 with faster, sharper generation

OpenAI released ChatGPT Images 2.5, a new image model that the company says delivers sharper details, more natural lighting, richer textures, and more reliable multi-turn editing. The model cuts image generation latency by up to 50% compared with Images 2.0, according to OpenAI's September 8 announcement.

The update adds product features in ChatGPT, including Sketch, which lets users draw directly in the chat as a reference for the final image, plus templates for popular formats like flyers and product photos. Users can now place comments directly on images for focused edits and share the prompts behind their images.

For developers, OpenAI introduced two API models: GPT-Image-2.5 Flare, which carries the quality and speed improvements, and GPT-Image-2.5 Sunburst, which offers extra precision for detailed work at longer generation times. Images 2.5 is available to all ChatGPT, ChatGPT Work, and Codex users on desktop, mobile, and web.

OpenAI said people create more than 3 billion images weekly across ChatGPT Images and the GPT-Image API models.