ChatGPT Sketch turns your bad drawings into detailed AI images

OpenAI has announced the release of ChatGPT Images 2.5, introducing a novel way for users to direct image generation: through hand-drawn doodles. A new feature called Sketch allows users to draw directly within the ChatGPT interface and then provide instructions on how to transform that sketch into a finished image. Users can activate the Sketch feature by typing @Sketch into the chat box, which opens a dedicated drawing window. The tool is capable of turning simple mouse-drawn doodles into realistic photos based on specific user prompts. Additionally, users can now leave comments directly on specific parts of generated images to request precise changes, such as altering eye color or background elements. Regarding the core engine, OpenAI states that ChatGPT Images 2.5 produces images with more natural lighting and richer textures. It is also more adept at following editing instructions across multiple conversational turns. Furthermore, image generation latency has been reduced by up to 50% compared to version 2.0. ChatGPT Images 2.5 is currently available for ChatGPT, ChatGPT Work, and Codex users across desktop, mobile, and web platforms.