# Overview
`Stable Virtual Camera (Seva)` is a 1.3B generalist diffusion model for Novel View Synthesis (NVS), generating 3D consistent novel views of a scene, given any number of input views and target cameras.
# :tada: News
- March 2025 - `Stable Virtual Camera` is out everywhere.
# :wrench: Installation
```bash
git clone --recursive https://github.com/Stability-AI/stable-virtual-camera
cd stable-virtual-camera
pip install -e .
```
Please note that you will need `python>=3.10` and `torch>=2.6.0`.
Check [INSTALL.md](docs/INSTALL.md) for other dependencies if you want to use our demos or develop from this repo.
For windows users, please use WSL as flash attention isn't supported on native Windows [yet](https://github.com/pytorch/pytorch/issues/108175).
# :open_book: Usage
We provide two demos for you to interative with `Stable Virtual Camera`.
### :rocket: Gradio demo
This gradio demo is a GUI interface that requires no expertised knowledge, suitable for general users. Simply run
```bash
python demo_gr.py
```
For a more detailed guide, follow [GR_USAGE.md](docs/GR_USAGE.md).
### :computer: CLI demo
This cli demo allows you to pass in more options and control the model in a fine-grained way, suitable for power users and academic researchers. An examplar command line looks as simple as
```bash
python demo.py --data_path 
[Jensen (Jinghao) Zhou](https://shallowtoil.github.io/)\*, [Hang Gao](https://hangg7.com/)\*
[Vikram Voleti](https://voletiv.github.io/), [Aaryaman Vasishta](https://www.aaryaman.net/), [Chun-Han Yao](https://chhankyao.github.io/), [Mark Boss](https://markboss.me/)
[Philip Torr](https://eng.ox.ac.uk/people/philip-torr/), [Christian Rupprecht](https://chrirupp.github.io/), [Varun Jampani](https://varunjampani.github.io/)