OpenAI has taken a step forward in artificial intelligence development with the launch of ChatGPT Images 2.0, its revamped image generator that promises ultra-realistic results and greater accuracy in interpreting instructions. Following the recent introduction of GPT-5.4-Cyber, focused on cybersecurity, the company led by Sam Altman reinforces its commitment to visual innovation. ChatGPT Images 2.0, powered by the GPT Image 2 model, introduces significant improvements in image creation, allowing users to generate up to eight images simultaneously with visual coherence in characters, objects, and styles. Additionally, the tool can search for information online, analyze files uploaded by the user, and examine the composition before creating the final image. This update is available for ChatGPT Plus, Pro, Business, and Enterprise subscribers, who will benefit from new reasoning and visual generation capabilities. Notable features include fidelity in detail reproduction, the ability to generate text in multiple languages—including Japanese, Korean, Chinese, Hindi, and Bengali—and compatibility with resolutions up to 2K and various image formats, from ultra-wide (3:1) to extreme vertical (1:3). OpenAI notes that these improvements open new possibilities for creating manga pages, graphic collections for social media, and visual space planning, among other uses. Users can already experiment with styles such as pixel art, manga, or cinematic shots, benefiting from higher quality and versatility in image generation.