OpenAI’s ChatGPT can now create images from text descriptions. The feature is part of the company’s latest update to its AI assistant. Users provide prompts, and the system generates visuals in minutes. This change follows growing demand for AI tools that produce images without specialized software.
The update was announced on the company’s website. It allows users to refine images by adjusting prompts. For example, specifying colors, styles, or details improves results. The system handles requests in plain language, making it accessible to non-technical users.
ChatGPT uses a model trained on image-text pairs. This enables it to interpret descriptions like "a sunset over mountains in watercolor style" accurately. The quality depends on prompt clarity. Vague instructions produce varied outcomes, while precise ones yield better matches.
The feature is available to subscribers of ChatGPT Plus. It integrates with existing tools, so users can export images directly. OpenAI did not disclose technical limitations or future improvements. The update reflects broader trends in AI-driven creativity.
Industry analysts see this as a step toward reducing reliance on design software. Competitors like Midjourney and DALL·E already offer similar functions. ChatGPT’s version stands out for its integration with a conversational AI platform.
Source: openai.com