Stability-AI/stable-virtual-camera
A diffusion-based generative model for novel view synthesis that creates 3D-consistent multi-view images and video from arbitrary camera poses.
Not currently ranked — collecting fresh signals.
star history
Stable Virtual Camera (SEVA) is a generalist diffusion model for novel view synthesis. It generates 3D-consistent multi-view images and video given an input image and target camera pose. The model is trained to synthesize new viewpoints of scenes, supporting applications in virtual camera control, 3D reconstruction, and view interpolation. Released with a HuggingFace model card and a Gradio demo for interactive use.
Frequently asked
- What is Stability-AI/stable-virtual-camera?
- A diffusion-based generative model for novel view synthesis that creates 3D-consistent multi-view images and video from arbitrary camera poses.
- Is stable-virtual-camera open source?
- Yes — Stability-AI/stable-virtual-camera is an open-source project tracked on heatdrop.
- What language is stable-virtual-camera written in?
- Stability-AI/stable-virtual-camera is primarily written in Python.
- How popular is stable-virtual-camera?
- Stability-AI/stable-virtual-camera has 1.6k stars on GitHub.
- Where can I find stable-virtual-camera?
- Stability-AI/stable-virtual-camera is on GitHub at https://github.com/Stability-AI/stable-virtual-camera.