OpenAI Launches ChatGPT Images 2.5 With Sketch and Precise Editing

OpenAI has introduced an updated version of ChatGPT Images 2.5, adding new features such as Sketch, templates, image comments, and more precise editing. The new version, launched on Tuesday, boasts sharper details, natural lighting, richer textures, and faster generation times compared to its predecessor, Images 2.0. Users can now edit images more accurately without altering the entire picture, even across multiple rounds of edits.

The inclusion of Sketch allows users to doodle directly in ChatGPT, guiding the final image based on their rough drawings. Templates for common formats like posters and merchandise have also been added. OpenAI released two new API models, GPT-Image-2.5 Flare and GPT-Image-2.5 Sunburst, catering to different use cases. The company maintains its safety checks, including C2PA metadata and invisible watermarking, to ensure the authenticity of AI-generated images.

OpenAI aims to make image generation more intuitive and engaging, enabling users to express their creativity without becoming prompt-engineering experts. The updated feature set is now available to all ChatGPT, ChatGPT Work, and Codex users across desktop, mobile, and web platforms.