Stability AI has released Stable Virtual Camera, a new multi-view diffusion model that transforms 2D images into videos. According to Ana Guillen, the research preview enables users to generate immersive videos with realistic depth and perspective without complex reconstruction or scene-specific optimization. The model can create videos from a single image or up to 32 images, following user-defined camera paths or 14 preset trajectories including 360°, spiral, and dolly zoom options. Stable Virtual Camera outperforms existing models in novel view synthesis benchmarks. The technology supports multiple aspect ratios and can generate videos up to 1,000 frames long. Currently available for research under a Non-Commercial License, the model has limitations with humans, animals, and complex scenes.