A new 3D video generation technology, Stable Virtual Camera, has arrived!
Introducing Stable Virtual Camera: A New Technology for 3D Video Generation
Original: Introducing Stable Virtual Camera: Multi-View Video Generation with 3D Camera Control — Stability AI
Importance: 新しい3D動画生成技術の発表で、多くのユーザーに影響を与える
Summary
Stability AI has introduced Stable Virtual Camera, a multi-view diffusion model that transforms 2D images into 3D videos. This technology does not require complex reconstruction or scene-specific optimization and generates realistic depth and perspective from up to 32 input images following user-defined camera trajectories. It is available for research use under a non-commercial license.
Key Points
- Generates 3D videos from 2D images
- Supports up to 32 input images
- User-defined camera trajectories supported
- Compatible with various aspect ratios
- Available for research under a non-commercial license
View developer notes (APIs, breaking changes, migration)
Stable Virtual Camera is a multi-view diffusion model that generates 3D videos from 2D images. It supports dynamic camera control with various trajectories such as 360° and Spiral. The model can produce videos in multiple aspect ratios and maintains 3D consistency for up to 1,000 frames. It is available for research under a non-commercial license.
Outlet: Stability AI
This article is an AI-generated summary (OpenAI GPT-4o-mini) of publicly available information from Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, Sakana, and other vendors. The original source URL is always provided in accordance with fair-use citation requirements. Summaries are AI-generated and may contain mistranslations or misinterpretations. Always verify details with the original source.