Washington, July 08 (QNA) - Meta announced the launch of Muse Image, its first AI-powered image generation model built by its AI unit, Superintelligence Labs.
The model will be integrated into image creation tools of Meta AI, Instagram, and WhatsApp, with plans to expand to Facebook and Messenger in the future.
The Muse Image model is part of a new family of Muse models that Meta plans to adopt instead of its Llama series, as part of its strategy to develop a new generation of AI technologies.
Head of Meta Superintelligence Labs (MSL) Alexandr Wang explained that the model has agentic capabilities, working in conjunction with the Muse Spark big language model to understand user requests, conduct online research, and plan before generating images, thus enhancing the accuracy and quality of the results.
He added that it is also preparing to launch the Muse Video model for generating videos, noting its strong performance in adhering to text commands, image quality, and maintaining frame consistency.
One of the most notable features of Muse Image is the ability to tag other Instagram accounts using the @ symbol within image creation commands, allowing the model to utilize the public images of those accounts to build a visual representation of their owners within the generated results.
Meta affirmed that users have control over how public images are used by AI tools through the platform's privacy settings.
The model allows direct image editing by drawing on them to add or remove elements, then sharing the results via posts, stories, or conversations within Meta apps.
The company announced that Muse Image will initially offer 30 new AI-powered effects in Instagram Stories in the US, with plans to expand the feature to more countries and other Meta apps later. (QNA)