OpenAI has launched ChatGPT Images 1.5, a new and upgraded image-generation and editing feature that makes it easier for users to create new images or modify existing ones. OpenAI CEO Sam Altman shared details about the update on Wednesday, saying the new model delivers results that closely match what users actually intend.
New image tools inside ChatGPT
With Images 1.5, ChatGPT now features a dedicated Images tab, allowing users to create and edit visuals in a more interactive way. During the launch, Sam Altman demonstrated how users can turn photos into 3D dolls, sketches, plush toys, doodles, vacation-style images, and more. The tools are designed to be intuitive, making image creation both fun and simple.
Users can also create holiday greeting cards, restore and retouch old photographs, convert images into famous art styles, design keychains, album covers, or even get outfit-matching suggestions. According to Altman, the feature is easy to use even for beginners and doesn’t require technical skills.
Images 1.5 now available to everyone
Altman confirmed that Images 1.5 is now live in ChatGPT and also available through the API, making it accessible to developers as well. The new version promises better image quality, faster generation, and improved editing tools. To mark the launch, Altman shared an image of himself edited as a firefighter using the new feature.
Improved photo editing and realism
OpenAI says Images 1.5 understands user instructions more accurately than earlier versions. Clothing and hairstyle try-ons now look more realistic, style changes are smoother, and important details of the original image are preserved. Users can easily add or remove elements, merge multiple images, or change layouts without affecting the entire photo.
Another key highlight is partial image editing. Users can now modify only a specific part of an image while keeping the rest unchanged. This includes changing colors, adding objects, removing backgrounds, or applying new styles to selected areas.
Pre-made styles and creative flexibility
ChatGPT Images 1.5 also introduces pre-made styles, reducing the need for long and detailed prompts. Users can apply creative effects quickly while still maintaining control over the final output. The model can also combine multiple images into a single scene seamlessly.
Competition with Google intensifies
The launch of Images 1.5 places OpenAI in direct competition with Google, which recently introduced advanced image-editing features in Gemini, including its Nano Banana tools. With easier controls, faster output, and powerful editing options, OpenAI is signaling its readiness to compete head-on in the AI image generation space.
