A new feature called Sketch, introduced as part of OpenAI's ChatGPT Images 2.5, allows users to turn rough sketches into detailed images. This tool lets users draw directly in the chat window using a simple set of pencils and colors. Once a sketch is created, users can provide instructions for how they want the image to be transformed. The tool is available to all ChatGPT, ChatGPT Work, and Codex users and can be accessed through the ChatGPT website, desktop applications, and mobile apps. To use Sketch, users open a new chat window and type @Sketch to bring up the drawing interface. Within this interface, users can choose from several built-in image models such as "figurine," "statue," "anime," "sticker," and "icon." These models help add specific styles or descriptions to the drawing. Users can also add text and shapes, erase parts they don’t like, and undo their actions. After the image is generated, users have the option to make further edits, add comments, erase sections, remove the background, or resize the image. A user with limited artistic experience tested the tool by submitting simple sketches. One sketch of a person wearing a hat was interpreted by ChatGPT as a turkey wearing a pilgrim hat. Another sketch of a character with messy hair was transformed into a humorous comic-style character. A third sketch, using the "figurine" model, became a detailed footballer figurine. The user found the results to be both creative and versatile, suitable for sharing online or using professionally. The Sketch tool demonstrates how AI can assist in creative processes, allowing even those without artistic training to produce visually appealing images. It offers a range of customization options and is designed to be user-friendly, making it accessible to a wide audience. OpenAI continues to expand the capabilities of its AI tools, aiming to make them more practical for everyday use.