OpenAI announces the launch of ChatGPT Images2.0 image model, significantly enhancing the ability to handle complex visual tasks

BlockBeats News, April 22 — OpenAI has launched ChatGPT Images 2.0, an image model that significantly enhances the ability to handle complex visual tasks, with upgrades in instruction understanding, object placement and relationship expression, as well as high-density text rendering. The model supports multilingual text generation, accurately presenting non-English content within images and improving overall semantic coherence.

In terms of generation capabilities, ChatGPT Images 2.0 allows for more detailed control, including small fonts, icons, UI elements, and complex compositions, supporting output resolutions up to 2K. It also further enhances style expression and realism, reliably generating photo-level images, cinematic styles, pixel art, and comics, suitable for scenarios such as game development, storyboarding, and marketing material creation. It possesses end-to-end task processing capabilities, enabling a complete workflow from copywriting to design composition.

ChatGPT Images 2.0 is now available to all ChatGPT and Codex users, with the “thinking” image features accessible to Plus, Pro, and Business users (Enterprise support coming soon). The underlying model gpt-image-2 is also available via API access.