OpenAI Launches Images 2.5 With Features Like Sketch, Comments, and More

OpenAI has launched Images 2.5, the latest generation of its image-generation technology. The ChatGPT maker claims Images 2.5 delivers improved results over its previous image-generation model. OpenAI says people generate more than 3 billion images with ChatGPT every week. It claims that the new state-of-the-art image model brings sharper details, more precise editing, and faster generation to creative workflows. The company has also introduced GPT‑Image‑2.5 Sunburst and GPT‑Image‑2.5 Flare, new API models alongside ChatGPT Images 2.5. 

ChatGPT Images 2.5 Features

OpenAI detailed ChatGPT Images 2.5 in a blog post on Tuesday. The company says the new model produces more natural lighting and richer textures while reducing latency by 50 percent compared with its previous image-generation model, Images 2.0. It has also added features like Sketch, templates, and comments.

Sketch is a new feature that lets users draw directly in ChatGPT as a reference for their final image. It can be accessed by typing @sketch in the ChatGPT composer. This tool is designed for converting early ideas into concepts. Templates are added in the Images tab, and it can ask follow-up questions based on a user's input to generate more personalised results. The company says Templates make it easier to start creating across image formats, like flyers and product photos.

Another new feature allows users to share their prompts alongside generated images. This lets friends or other users use the same prompt to create their own versions of an image.

ChatGPT Images 2.5 is now available to all ChatGPT, ChatGPT Work, and Codex users across desktop, mobile, and web.

OpenAI has also unveiled the GPT‑Image‑2.5 Sunburst and GPT‑Image‑2.5 Flare API models alongside ChatGPT Images 2.5. The GPT‑Image‑2.5 Flare is designed as the standard model for most applications. It is also claimed to deliver higher-quality images than GPT‑Image‑2 at 50 percent lower latency. It is suitable for creator and social content, product experiences, visual search, rapid image prototyping, and high-volume generation.

The GPT‑Image‑2.5 Sunburst is built specifically for high-precision, premium visual workflows. It follows specific editing instructions more reliably across multiple edits. OpenAI says it is ideal for production-ready campaign creative or polished product imagery.