NVIDIA · Reactor SANA-Streaming
SANA-Streaming is a system-algorithm co-designed framework for high-resolution, real-time streaming video editing. Publish your webcam to the `camera` track, optionally steer with natural-language prompts, and watch the edited stream on `main_video`. NVIDIA researchers report 1280×704 output at 24 end-to-end FPS on a single RTX 5090. Roamscape runs it through the typed `@reactor-models/sana-streaming` SDK with pause, resume, reset, and live prompt updates.
Overview
| Status | Live in Roamscape |
|---|---|
| Access | Runnable in Roamscape |
| Released | 2026 |
| Inputs | source video stream, text edit prompt, local edit regions, background replacement prompts, style-transfer prompts |
| Outputs | real-time edited video stream, 1280×704 streaming output, temporally consistent V2V frames, physical-AI augmented sensor video |
| Best for | real-time streaming video editing, live broadcast and gaming overlays, style transfer on video streams, autonomous-driving sensor augmentation, robotics egocentric video transformation, minute-length causal V2V, physical-AI synthetic data |
Why it matters
SANA-Streaming sits between live world models and classical video editors: it transforms existing video streams in real time with prompt control, temporal consistency, and physical-AI use cases such as autonomous-driving sensor augmentation and egocentric robotics sim-to-real. It expands Roamscape’s Train and Play index beyond generative 3D into streaming V2V editing.
Roamscape use
Live in Roamscape at /live — member sessions with webcam input, optional edit prompts, pause/resume, and real-time V2V output.
Strengths
- 24 FPS end-to-end on a single RTX 5090
- minute-length causal streaming edits
- preserves source motion and unedited content
- hybrid DiT with GDN + softmax attention
- cycle-reverse regularization for temporal consistency
- strong physical-AI demo coverage (AV, robotics)
- public Reactor-hosted demo
Limitations
- video-to-video editing, not exportable 3D worlds
- requires a live webcam stream as source video
- member-only in Roamscape (camera + credits)
- hardware targets high-end consumer GPUs on the host
- prompt is optional — without one the output stays close to the camera input