OpenAI launches enhanced image generation model with advanced features

OpenAI has launched ChatGPT Images 2.5, a new state-of-the-art image model that offers sharper details, faster generation, and more precise editing. The update is available to all ChatGPT, ChatGPT Work, and Codex users across desktop, mobile, and web. Images 2.5 reduces generation latency by up to 50% compared to Images 2.0, enabling quicker refinement of creative concepts. It also improves the ability to follow editing instructions across multiple turns, ensuring consistency in long conversations. The release includes new features such as Sketch, which allows users to draw directly in ChatGPT as a reference for final images, and templates for popular formats like flyers and product photos. Users can now add comments to images for focused editing and share prompts to let others build on their ideas. Two new API models, GPT‑Image‑2.5 Flare and GPT‑Image‑2.5 Sunburst, offer enhanced quality, speed, and precision for developers. OpenAI emphasized the model’s ability to maintain image quality over multiple edits and its improved handling of complex visual instructions. Early customer feedback highlights the model’s reliability in production workflows and its capacity to generate on-brand creative assets. The update is now live for all users, with API models available for developers.