OpenAI Rolls Out Major Upgrade to ChatGPT Images to Rival Google's Nano Banana

OpenAI has launched a new version of ChatGPT Images, powered by its latest flagship image generation model, delivering faster performance, stronger instruction-following and more precise editing capabilities for users worldwide.

The update, now available in ChatGPT and as the GPT Image 1.5 API, aims to make AI-powered creative tools more practical and reliable for both everyday users and enterprises.

This comes after Google unveiled Nano Banana Pro, a Gemini 3 Pro–powered image model that turns ideas, notes, prototypes and real-time information into visuals, while tapping directly into Google Search’s vast knowledge base.

According to OpenAI, the upgraded system generates images up to four times faster than previous versions while preserving important visual elements like lighting, composition and facial likeness, even through multiple edits.

Users can create original images or transform existing ones — adding, subtracting, combining or blending elements — without losing the essence of the original content.

The new ChatGPT Images experience includes a dedicated Images interface, making it easier to explore presets, styles and creative ideas without needing specialised prompts.

OpenAI noted that the model excels at both simple adjustments and more complex creative transformations, from concept art to stylistic edits.

“GPT Image 1.5 generates high-fidelity images with strong prompt adherence, preserving composition, lighting, and fine-grained detail,” OpenAI said in its announcement, adding that the results are “clean, realistic, and reliable,” supporting faster workflows across creative applications.

The updated image tool is available immediately to all ChatGPT users, with Business and Enterprise access rolling out soon. The GPT Image 1.5 model is also accessible via OpenAI’s API, enabling developers and companies to integrate the enhanced imaging capabilities into their own products and services.