ChatGPT’s new Images 2.0 model is surprisingly good at generating text
OpenAI's ChatGPT Images 2.0 model has significantly improved text generation in images, making it nearly indistinguishable from human-made content. The new model is available to all ChatGPT and Codex users, with paid users able to generate more advanced outputs.
OpenAI has released ChatGPT Images 2.0, a new model that generates high-quality images with accurate text. The model has 'thinking capabilities' that allow it to search the web, create multiple images from one prompt, and double-check its creations. Images 2.0 can produce marketing assets in various sizes and multi-paneled comic strips, and has a stronger understanding of non-Latin text rendering. The model's knowledge cuts off in December 2025, which may impact its ability to generate certain prompts involving recent news. All ChatGPT and Codex users will have access to Images 2.0, with paid users able to generate more advanced outputs. The gpt-image-2 API will also be available, with pricing dependent on output quality and resolution.
This content was automatically generated and/or translated by AI. It may contain inaccuracies. Please refer to the original sources for verification.