Video Runtime
Developer-onlyFrame-StreamingOfficial source

StreamDiffusionV2

Build interactive video streams with a diffusion system designed for configurable GPU pipelines.

Access and release status are source-checked descriptions, not a live uptime check. A reachable website does not establish that video playback or interaction currently works.

Open Documentation ↗View GitHub ↗

No rights-cleared product preview yet. See the official page for its latest interface.

Published by Video Runtime · Source check 2026-09-05 · Evidence method · Suggest a correction

EDITORIALLY VERIFIED PRODUCT INFORMATION

About StreamDiffusionV2

Build interactive video streams with a diffusion system designed for configurable GPU pipelines. Combines streaming video diffusion with configurable denoising and a sliding-window attention cache.

Key features

Supports different GPU configurations and is also available as a pipeline inside Daydream Scope.

Getting started

Open the official repository, read its current README and licence, then follow the documented environment, checkpoint and inference steps. Start with the supplied example before using your own media or data.

Real-time interaction

Combines streaming video diffusion with configurable denoising and a sliding-window attention cache.

Pricing

Apache-2.0; compute costs extra Repository code: Apache-2.0. Model weights and dependencies may have separate terms. No hosted price is estimated here. Budget for your own GPU or cloud usage after testing a representative workload.

Limitations

Requires Linux and a compatible NVIDIA GPU; local setup is needed before an interactive session can run.

Read the documentation ↗

EDITORIAL VIEW

Editor's Verdict

Consider StreamDiffusionV2 if its documented workflow matches your experiment; start from the linked repository rather than an unofficial mirror.

Check the licence and run a small local evaluation before choosing it for production. No ratings or measured results are inferred from its publication.

How It Works

  • Combines streaming video diffusion with configurable denoising and a sliding-window attention cache.

What We Like

  • Supports different GPU configurations and is also available as a pipeline inside Daydream Scope.

Current Limitations

  • Requires Linux and a compatible NVIDIA GPU; local setup is needed before an interactive session can run.

Pricing & Access

  • Repository code: Apache-2.0. Model weights and dependencies may have separate terms.
  • No hosted price is estimated here. Budget for your own GPU or cloud usage after testing a representative workload.

Verification Summary

  • Official repository and licence reviewed on 2026-09-05. Video Runtime has not installed or benchmarked this project.
  • This is a source review, not verification of demo uptime, output quality or performance on your hardware.
Technical notes & official performance

Official Performance Data

  • Authors describe high-throughput streaming. GPU count, denoising steps and decoding choices affect results; no universal end-to-end latency is claimed here.

Technical Notes

  • The current repository documents ring-buffer KV caching, optional lightweight VAE decoding and initial Blackwell support.

Sources

  1. Official GitHub repository ↗github · accessed 2026-09-05
  2. Code licence ↗github · accessed 2026-09-05
  3. Official project documentation ↗official-docs · accessed 2026-09-05

Access, stage & mechanism

These are separate source-checked facts, not a live uptime monitor. Unverified fields are left open; transport and persistent sessions do not establish how frames are generated.

Release stage
Not verified
Access mode
Not verified
Source availability
Not verified
Transport
Not verified
Interaction
Not verified
Session mode
Not verified
Generation mechanism
Not verified
Continuity method
Not verified
Licence status
Not verified
Tasks
Not classified

Read how official-source and hands-on records stay separate in our Methodology.