OpenAI has taken a significant step in AI-powered image creation technology by introducing ChatGPT Images 2.0. This new version allows users to produce higher quality visuals by better following instructions and maintaining desired details. Additionally, its ability to generate multiple images with a single command is noteworthy.
Advanced Features and Use Cases
ChatGPT Images 2.0 revolves around three key elements that enhance user experience: typography, language diversity, and consistency. When the thinking model is activated, this system can gather data from online sources to create visuals that match the uploaded files. Moreover, it has the capability to evaluate the structure of the visuals logically.
Furthermore, this new model can produce up to eight images simultaneously while preserving the same characters and objects in each scene. According to OpenAI, these features will facilitate the work of content creators, providing efficiency in projects like manga pages or social graphics.
Users can now design images in higher resolutions and various aspect ratios. Notably, the ability to effectively create visuals in languages such as Japanese and Korean, in addition to English, stands out as a significant achievement.
A New Era Begins
OpenAI has phased out the previous model, GPT-Image-1.5, while stating that the features of the new model will be available to subscribers of ChatGPT Plus, Pro, and Business. Free users will have access to the basic ImageGen 2.0 model. Additionally, the company will also make the gpt-image-2 API available.