Meta
Open research AI models for image generation and 3D creation
Meta produces widely adopted open-weight models that cover image generation, video synthesis, and 3D reconstruction. Releases like SAM and LLaMA have shaped the broader AI ecosystem by making high quality research accessible to developers everywhere. As a Runware provider, Meta models are available through a single inference pipeline alongside other creators.
Models by Meta
Muse Image is Meta's flagship image generation model from Meta Superintelligence Labs. It is built for prompt-faithful image creation, precision editing, and multi-reference composition, with strong text rendering and the ability to refine existing photos through localized markup-based edits. Meta positions it as an agentic image model that plans layouts, uses search and coding tools to improve accuracy, blends multiple visual references intelligently, and handles both creative generation and practical visual tasks such as infographics, QR codes, restorations, product-style mockups, and photobomber removal.
SAM 3D Objects is a foundation 3D model from Meta that reconstructs full 3D shape geometry, realistic texture, and scene layout of objects from a single RGB image. It produces high-fidelity 3D meshes robustly even in cluttered, occluded real-world scenes, and significantly outperforms prior single-image 3D methods. SAM 3D Objects is part of the broader SAM 3D family, enabling 2D-to-3D reconstruction workflows for visualization, AR/VR, robotics, and digital content creation.