The technology company OpenAI has announced the launch of a new feature in its AI model GPT-4o that promises enhanced quality in generated images.
Announcement of GPT-4o Updates
OpenAI CEO Sam Altman announced on the platform X (formerly Twitter) about the release of the new capability of the GPT-4o model. He stated that this technology provides incredible opportunities for creating images and expressed confidence that users will love it.
Features and Capabilities of GPT-4o
The new feature allows users to create images with embedded text, symbols, and diagrams. With multi-turn generation capability, users can refine their images through dialogue with AI. This feature is beneficial for designers and other creative uses where visual consistency is key. The image instruction feature also allows up to 10-20 objects in a scene, with support for in-context learning.
Availability and Future Development
Currently, the new image generation feature is available to ChatGPT Plus, Pro, Team, and Free users by default. Access for enterprise and educational users is expected soon, along with API support.
With the launch of the new image feature in GPT-4o, OpenAI continues to enhance its technology's capabilities and support user creativity, with a focus on the quality and functionality of images.
