Original Source
OpenAI Unveils 'Images 2.0' Image Generator, Ushering in AI Image Renaissance
OpenAI Emphasizes Advancement in Image Generation Technology
OpenAI has unveiled ChatGPT Images 2.0, marking a new leap in artificial intelligence image generation technology. The company stated that this new model represents a significant advancement over previous image generation capabilities, likening it to a jump from 'GPT-3' to 'GPT-5' all at once. Through a promotional advertisement, OpenAI compared 'DALL-E' to 'cave drawings' and 'Images 1.0' to 'ancient art,' emphasizing that Images 2.0 signifies a 'renaissance' in the field.
Key Features and Modes of 'Images 2.0'
Images 2.0 boasts enhanced multilingual capabilities, improved visual intelligence, and closer attention to detail. The model also offers two modes: instant and thinking. The instant mode is a faster and revamped version of a typical image generator, available to all ChatGPT and API users. In contrast, the thinking mode provides more complex functionalities and is exclusively available to paid subscribers of Plus, Pro, and Business plans.
When the thinking mode is selected, Images 2.0 can search the web for real-time information, create multiple distinct images from a single prompt, and double-check its own outputs. OpenAI announced that the thinking mode can generate several pages of a manga comic with recurring characters and evolving storylines, or entire magazine pages from a single simple prompt.
*Source: Gizmodo (2026-04-21)*
