Artificial intelligence (AI) company OpenAI has released a new version of ChatGPT Images, powered by its latest image generation model. The update is designed to make creating and editing images faster and more precise, while keeping details like lighting, composition, and people’s appearance consistent.
According to the company, the new model can make precise edits to uploaded images, allowing users to change specific elements without altering the rest. It can also perform more complex transformations, such as adding or rearranging elements, applying stylistic filters, or reimagining concepts, while keeping the original image intact.
OpenAI says the model follows instructions more reliably than the previous version. It can handle intricate compositions and render text more accurately, including denser and smaller text.
The update is now available in ChatGPT for all users, with Business and Enterprise access coming later. OpenAI is also rolling out GPT Image 1.5 in its API. This version includes the same improvements for marketing, brand work, e-commerce, and other applications that require consistent image editing or generation. Image inputs and outputs in GPT Image 1.5 are about 20% cheaper than the previous model.
Companies across industries, from creative tools to e-commerce and marketing software, are already using GPT Image 1.5 for tasks such as product image catalogs, logo creation, and marketing graphics.