OpenAI Launches ChatGPT Images 2.5 With Faster Editing
News Desk
SAN FRANCISCO: OpenAI has launched ChatGPT Images 2.5, its latest image-generation model, with faster generation, sharper visual details and more precise editing capabilities.
According to OpenAI, the new model delivers more natural lighting and richer textures while improving its ability to preserve the appearance of people, objects and other subjects across multiple editing stages. Generation latency has also been reduced by up to 50 per cent compared with Images 2.0.
ChatGPT Images 2.5 is rolling out to ChatGPT, ChatGPT Work and Codex users across desktop, mobile and web.
One of the major additions is a new Sketch feature, which allows users to draw a rough idea directly in ChatGPT and use it as a visual reference for generating an image.
The update also introduces templates for popular formats such as posters and product images, while users can add comments to generated images to request more focused edits.
Another new feature allows users to share the prompt used to create an image. This means others can reuse the same creative idea while adapting it with their own images and details.
OpenAI has also introduced two new image-generation models for its API: GPT-Image-2.5 Flare, designed for faster high-quality generation, and GPT-Image-2.5 Sunburst, aimed at more detailed creative workflows where greater precision is required.
The company said the update is designed to give users greater control over the creative process while making image generation and repeated editing faster and more consistent.
