Kamal Ghorui
OpenAI has introduced ChatGPT Images 2.0, an updated version of its image generation model, ChatGPT Images. Announcing the new model, the company said: “ChatGPT Images 2.0 is the next step: a state-of-the-art model that can take on complex visual tasks and produce precise, immediately usable visuals”. OpenAI said that the new model is designed to handle complex image tasks and produce visuals that are more precise and usable. According to OpenAI, the new model brings major improvements in how it follows instructions and handles detailed elements in images. It can render small text, icons and user interface elements more accurately, which has been a challenge for earlier image models.“This model is a step change in detailed instruction following, placing and relating objects accurately, and rendering dense text, with the ability to generate across aspect ratios. Its sense of composition and visual taste means results feel less AI-generated and more intentionally designed. It’s accurate across languages and uses its expanded visual and world knowledge to fill in the gaps for you, so you get smarter images with less prompting,” OpenAI said in the official announcement.
ChatGPT Images 2.0 features
OpenAI said ChatGPT Images 2.0 also improves performance across languages. The model can generate text within images in languages such as Japanese, Korean, Chinese, Hindi and Bengali with higher accuracy. That includes not just translating a label or two, but generating visually coherent outputs where language is part of the design itself, from posters and explainers to diagrams and comics.This means users can create visuals like posters, diagrams and comics that include non-English text, with better readability and structure.The updated model introduces “thinking” features, which allows it to handle more complex tasks. When used with advanced modes, the model can search for real-time information, generate multiple images from a single prompt and check its own outputs.OpenAI said this helps users move from idea to final image more efficiently, especially for tasks that require accuracy and consistency.ChatGPT Images 2.0 supports a wider range of visual styles, including photorealistic images, illustrations, comics and cinematic visuals. It also allows users to generate images in different aspect ratios, making it suitable for formats such as social media posts, presentations and banners.The model can produce outputs that better match the requested style, with improvements in lighting, texture and composition.
ChatGPT Images 2.0 availability and use cases
The new model is available to all users through ChatGPT, Codex and the API starting today. Advanced outputs with thinking are available to ChatGPT Plus,Pro, and Business users. The gpt-image-2 model is available in the API; pricing varies depending on the selected quality and resolution of the image.OpenAI said it can be used for tasks such as marketing design, educational content, storytelling and product development. Developers can also integrate the model into their own applications using the API, allowing for automated image generation and editing workflows.
