OpenAI adds new features to ChatGPT image generation tool

OpenAI has rolled out an updated image creation and editing feature within ChatGPT, expanding how users can generate and modify visuals, the ChatGPT maker said. Image generation is among the top uses of the chatbot in India, according to the parent company.

The update introduces a dedicated Images section within the chatbot, accessible through the model or tool menu or via the sidebar. The new setup is aimed at improving how users create, edit and refine images.

The updated image model follows instructions more closely, including finer details, while maintaining consistency in lighting, composition and facial features. This is said to allow for more accurate edits, realistic transformations and image adjustments that preserve key elements of the original visual.

The update also improves generation speed. Users can start creating new images while others are still processing, which is intended to make iterative tasks such as refining designs or removing elements more efficient.

A new Images workspace has also been added, featuring preset filters, trending prompts and an option for one-time likeness uploads.

The update reflects a shift toward practical use of AI-generated images, with a focus on accuracy, control and speed. The chatbot parent highlighted potential applications for creators, designers, educators and businesses in India seeking visuals that reflect local contexts and cultural details.

The updated ChatGPT Images feature is rolling out globally to all models and API users. OpenAI said the earlier image model will remain available as a custom GPT.