OpenAI releases faster ChatGPT image generation model

OpenAI released an updated version of its ChatGPT image generation tool, powered by a new model called GPT Image 1.5. The company said the new system generates images up to four times faster than the previous version and provides more precise editing capabilities.

The updated ChatGPT Images feature is rolling out to all ChatGPT users and is available through OpenAI's API. The model maintains details like lighting, composition, and facial appearance when making edits to uploaded images, according to the company.

OpenAI said the system can perform various editing functions including adding, subtracting, combining, and blending elements in images. The model also demonstrates improved text rendering capabilities, handling denser and smaller text within generated images.

The company introduced a new Images feature within ChatGPT's sidebar that includes preset filters and trending prompts. Users can upload their likeness once and reuse it across future image creations without repeatedly accessing their photo library.

The system allows users to continue generating new images while others are still processing, enabling faster iteration during creative projects. OpenAI stated that users can now create images through text descriptions or by selecting from preset styles and ideas within the interface.

Microsoft (NASDAQ: MSFT) has a significant investment in OpenAI and integrates the company's AI models across various Microsoft products and services. The new image generation capabilities represent OpenAI's latest advancement in multimodal AI technology.

You May Also Be Interested In