The latest update to ChatGPT Images 2.0 enables the creation of multiple images from a single prompt. OpenAI has introduced enhanced “thinking capabilities” to its AI-driven image generator, allowing it to search the web for creating sophisticated images. The new version improves following instructions, detail preservation, and text generation. Backed by OpenAI’s GPT Image 2 model, these thinking features are available to ChatGPT Plus, Pro, Business, and Enterprise users. The image generator can source information online, create visual explanations from uploaded files, and understand the structure before image generation. ChatGPT Images 2.0 can generate up to eight images simultaneously with consistent characters, objects, and styles. This enhances the creation of manga pages, social graphics, or house design plans. The update also improves capturing photo characteristics and supports various image types like pixel art and cinematic stills. It offers a resolution up to 2K with diverse aspect ratios and excels in generating images with text in languages like Japanese, Korean, Chinese, Hindi, and Bengali. Initially released last year, ChatGPT Images has evolved with faster generation and better photo editing. Competition includes tools like Google’s Nano Banana Pro and Microsoft’s MAI-Image-2. ChatGPT Images 2.0 is now available for all ChatGPT and Codex users.
OpenAI’s updated image generator can now access web information
1 Min Read