Key Points
- OpenAI releases GPT-Image-1.5, a new AI image model.
- Model operates roughly four times faster than its predecessor.
- Improved instruction following and editing tools for precise image control.
- Enhanced ability to render legible text within generated images.
- Available to all ChatGPT users worldwide via a dedicated sidebar space.
- Accessible through API for developers.
- Launch coincides with competition from Google’s Nano Banana Pro.
- Follows OpenAI’s partnership with Disney to expand character libraries.
Overview of the New Model
OpenAI announced the release of GPT-Image-1.5, its latest AI image generation model. Designed to be significantly faster, the model operates at roughly four times the speed of the earlier version while delivering higher fidelity in interpreting user prompts.
Key Features and Capabilities
The new model emphasizes better adherence to instructions, enabling users to request specific objects, style changes, or precise edits. It also introduces tools that let users add or remove elements within an image, try on particular clothing items, and adjust visual styles. A notable improvement is its ability to render legible text within images, a task that has historically challenged generative models.
Availability and Integration
GPT-Image-1.5 is now available to every ChatGPT user globally. It can be accessed through a dedicated space in the ChatGPT interface, located in the sidebar, where users can select preset styles and explore trending designs. Developers can also integrate the model into their applications via the API, identified as GPT-Image-1.5.
Competitive Landscape
The launch arrives amid heightened competition in AI image generation. Google recently promoted its Nano Banana Pro tool, which leverages the Gemini 3 model to produce hyper‑realistic images and legible text. OpenAI’s new offering positions itself as a direct response to that advancement, aiming to attract both casual users and creators seeking more precise visual output.
Partnerships and Industry Context
OpenAI’s rollout follows a broader strategic push, including a recent agreement with Disney to incorporate over 200 iconic characters into future ChatGPT image and video capabilities. While the Disney content will become available later, the partnership underscores OpenAI’s intent to expand its visual library and appeal to a wider audience.
Overall, GPT-Image-1.5 represents a substantial step forward for OpenAI, combining speed, precision, and user-friendly tools to enhance the creative possibilities within the ChatGPT ecosystem.
Source: cnet.com