California (Web Desk) — Technology company OpenAI has introduced its latest image-generation model, ChatGPT Images 2.5, which is available on ChatGPT, ChatGPT Work and Codex.
According to the company, the new model generates images faster than Images 2.0, released in April, while its editing capabilities and ability to preserve the appearance of characters and objects in images have also been improved.
OpenAI says Images 2.5 produces more natural lighting and more realistic textures, while its ability to preserve elements of the original image during edits across multiple stages has also become more effective. Image generation time has been reduced by up to 50 percent compared with Images 2.0.
The new model also includes a feature called Sketch, which allows users to draw a simple outline of an image or composition directly in ChatGPT and use it as a visual guide for creating the final image.
In addition, users can now share the prompt used to create an image along with the image itself, allowing others to reuse the same idea with their own images and details.