OpenAI’s updated image generator can now pull information from the web
The Verge
OpenAI has launched ChatGPT Images 2.0, featuring web-search capabilities, improved text rendering, and the ability to generate consistent multi-image sequences.Summary
OpenAI has introduced ChatGPT Images 2.0, powered by the new GPT Image 2 model. This update enables the generator to perform web searches to reason through prompts, allowing for more sophisticated outputs and improved adherence to user instructions. Key enhancements include the ability to generate up to eight consistent images simultaneously, higher resolution (up to 2K), and a wider range of aspect ratios. Furthermore, the model has significantly improved its text-rendering capabilities for non-Latin scripts, including Japanese, Korean, Chinese, Hindi, and Bengali.
(Source：The Verge)