OpenAI has announced the release of ChatGPT Images 2.5, which includes a new feature called Sketch. This feature allows users to draw a doodle directly in ChatGPT and then provide instructions on how to turn it into a realistic image. The Sketch feature can be activated by typing @Sketch into the chat box, and a window will pop up where users can create their drawing.
In testing, the Sketch feature successfully turned a simple doodle of a cat into a realistic photo. Users can also leave comments directly on parts of images they want changed, making it easier to edit and refine the generated images. For example, users can ask ChatGPT to change the color of an object or add more details to the image.
ChatGPT Images 2.5 also includes several other improvements, including more natural lighting and richer textures in generated images. The new version is also better at following editing instructions across multiple turns, making it easier for users to refine their images. Additionally, image generation latency has been reduced by up to 50% compared to the previous version, making it faster and more efficient to generate images.
The new features are available now for ChatGPT, ChatGPT Work, and Codex users on desktop, mobile, and web. With the release of ChatGPT Images 2.5, OpenAI continues to improve its image generation capabilities, making it a more powerful tool for users who need to create detailed and realistic images.
Este artigo foi escrito com a assistência de IA.
News Factory APP - notícias agênticas para impulsionar seu SEO e AEO.