OpenAI showed the world a new generative model called ChatGPT Images 2. This is more than just your average image-generating tool. The new OpenAI Image 2 model can create magazine designs featuring both text and images. Users may basically create a magazine page or even an entire magazine through this feature. The move comes right after OpenAI announced the shutdown of Sora, its generative AI video model. The company revealed the upgrade during its latest livestream event.
Introducing ChatGPT Images 2.0
— OpenAI (@OpenAI) April 21, 2026
A state-of-the-art image model that can take on complex visual tasks and produce precise, immediately usable visuals, with sharper editing, richer layouts, and thinking-level intelligence.
Video made with ChatGPT Images pic.twitter.com/3aWfXakrcR
The capabilities extend far beyond magazine layouts. The OpenAI Image 2 model delivers 2K resolution images in multiple aspect ratios. It generates images using updated data from the web up to December 2025. The model features Instant and Thinking modes for different use cases. It can also add non-Latin languages to its expertise. This real-world intelligence comes from the updated knowledge cutoff combined with end-to-end task handling.
OpenAI is rolling out the latest model now. Users may try it once they see it available on the app or website platform. Initially, OpenAI’s solution to ChatGPT’s image generation relied on sharing DALL-E’s generative models. The company later changed that to the ChatGPT Image model in December 2025. That shift responded to the massive popularity of Google’s Nano Banana Pro. Now the OpenAI Image 2 model raises the bar even higher.
The new model handles text and images together seamlessly. Magazine designers may find their workflows transformed. Content creators can generate entire publications with minimal effort.
