OpenAI has rolled out an updated image generation model for its popular AI tool, ChatGPT. Dubbed ChatGPT Images 2.0, this version can churn out more than one image from a single prompt, including entire study booklets and detailed infographics. The new model also supports text in multiple languages, making it accessible to a global audience.

What sets Images 2.0 apart is its ability to tap into ChatGPT’s reasoning capabilities, allowing for more thorough and granular image generation. For instance, users can request an infographic with accurate weather details and realistic drawings of iconic San Francisco landmarks. The model even offers customizable aspect ratios, enabling users to generate images in a wide range of sizes.

Despite these enhancements, the new model still faces some challenges. When tested for text rendering, especially in non-English languages like Chinese, the output was mixed. While English text appeared clean and accurate, the translation feature flagged many parts as either fake or semi-gibberish. This suggests that while ChatGPT Images 2.0 has made significant strides, there is still room for improvement when it comes to international language support.

Overall, OpenAI’s latest release could reignite interest in AI-generated content, particularly among social media users who might find new creative ways to use the tool. However, the success of this model will depend on how well it handles different languages and whether its outputs align with user expectations globally.