Meta is expanding its generative AI image offerings with the rollout of Muse Image. Multiple reports say the tool is designed to understand text prompts, allowing users to generate images based on described requests. The rollout also highlights multimodal capabilities, including the ability to use photos as inputs when creating or refining images. In addition, Meta’s Muse Image supports editing workflows: users can modify AI-generated images using sketches as guidance. The coverage describes Muse Image as part of Meta’s broader effort to add more interactive features to its generative AI tools, aiming to make image creation and editing more flexible for users. While the articles focus on the main functions—prompt interpretation, photo input, and sketch-based editing—they do not provide contrasting claims about performance, availability by region, or specific pricing. The shared descriptions indicate that Muse Image is being positioned as an extension of Meta’s existing generative AI capabilities, with emphasis on easier transformation from text and visual references into edited images.