Source code</>
Daydream Scope
Experimental
Daydream Scope
A workbench for running real-time generative video pipelines, with model selection, composable processing and WebRTC, NDI, Spout or Syphon output paths.
Open source / Streaming video style translation
Live2Diff
A video-to-video research pipeline using one-way temporal attention to transform live input, with webcam and screen-video demos.
View repository ↗Source code</>
Live2Diff
The unlock
Why this one is on the map.
Addresses temporal consistency when processing a live feed without knowing future frames.
The clearest product signal is “Restyle a stream using past frames”. That interaction model—not a generic AI feature list—is the reason to compare it with the rest of this directory.
This is source code, not a hosted channel. You need to inspect, configure, and deploy it with your own keys and runtime before anything can broadcast.
How to read it
What happens when you open it.
Open the official destination and look for the current video-to-video · live input · research code workflow. Controls, access and live activity can change after this editorial check.
Best for: Streaming video style translation
Access note: Read the repository setup and license before running. Hardware, model downloads and API access vary by project.
Sources & status
Keep the link, keep the caveat.
2026-09-05: Official README reviewed at the open-mmlab repository. Code and checkpoint instructions available; reported speed depends on the documented GPU configuration.
Explore similar projects
Suggest a correction ↗Source code</>
StreamDiffusionV2
Experimental
StreamDiffusionV2
An interactive video-diffusion system with released checkpoints, configurable inference and support for different GPU arrangements.
Source code</>
UNREEL
Experimental
UNREEL
An open-source, self-hosted AI streaming service that writes scenes and renders MiniMax H3 Max Turbo video through fal as a channel plays.