In a significant upgrade to its popular AI chatbot, OpenAI has introduced a powerful new image editing feature for ChatGPT. The update, named GPT Images 1.5, transforms the platform from a text-based conversational agent into a versatile visual editor, allowing users to manipulate photos using simple text commands.
What's New in the GPT Images 1.5 Update?
The core of this update is a suite of advanced image manipulation capabilities directly within the ChatGPT interface. Users can now upload a photograph and instruct the AI to modify it through descriptive text prompts. The functionality goes beyond basic filters, enabling complex creative tasks.
The AI can understand and execute a wide range of editing commands. You can ask it to add new objects to a scene, remove or subtract existing elements seamlessly, and even combine multiple images into a single coherent picture. More advanced operations like blending styles, transposing objects from one image to another, and altering compositions are now possible with ease.
How to Access and Use the New Features
To use the new GPT Images 1.5 features, users need access to the ChatGPT platform, which now supports image uploads alongside text. The process is designed to be intuitive: upload your image, then describe the changes you want in plain English. For instance, you could prompt, "Add a rainbow over the mountain," or "Remove the person in the background and replace them with a tree." The AI interprets the request and generates an edited version of the image.
This move significantly lowers the barrier to entry for sophisticated photo editing, which traditionally requires software like Photoshop and considerable skill. OpenAI's update democratizes these capabilities, making them accessible to anyone who can describe what they envision.
Implications for the Future of AI and Creativity
The launch of GPT Images 1.5, reported on 17 December 2025, marks another bold step by OpenAI in integrating multimodal AI—systems that can process and generate different types of data like text and images. It positions ChatGPT as a more holistic creative tool, competing in the crowded generative AI space for visual content.
For everyday users, students, and content creators, this means faster turnaround for visual projects and the ability to prototype ideas without technical hurdles. However, it also raises important discussions about the authenticity of visual media and the need for clear labeling of AI-generated or AI-edited content.
By blending conversational AI with visual intelligence, OpenAI is not just updating a product; it is reshaping how humans interact with machines to bring their imaginative ideas to life, simply through the power of language.
