Video Runtime
Developer-onlyLive TransformationOfficial source

LiveEdit

Edit a streaming video with diffusion while reusing unchanged regions and extending to longer sequences.

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.

View GitHub ↗

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

Published by Video Runtime · Source check 2026-09-14 · Evidence method · Suggest a correction

EDITORIALLY VERIFIED PRODUCT INFORMATION

About LiveEdit

Edit a streaming video with diffusion while reusing unchanged regions and extending to longer sequences. Uses autoregressive diffusion and an action-oriented mask cache to avoid recomputing unchanged areas during instruction-guided video editing.

Key features

Includes single-GPU inference, long-video rolling attention and a token-pruning configuration with mask visualisation.

Getting started

Install the Linux/NVIDIA environment, download the linked base model and LiveEdit checkpoint, run the supplied short example, then try the separate long-video configuration.

Real-time interaction

Uses autoregressive diffusion and an action-oriented mask cache to avoid recomputing unchanged areas during instruction-guided video editing.

Pricing

Apache-2.0 code; self-hosted compute costs extra Repository code is published under Apache-2.0. Confirm separate model, dataset and dependency terms before reuse. No hosted price is inferred. Budget for the documented GPU, storage and setup requirements.

Limitations

The released checkpoint was trained on shorter sequences, so quality may degrade when rolling attention extrapolates far beyond that horizon.

Read the documentation ↗

EDITORIAL VIEW

Editor's Verdict

LiveEdit is included as a source-available implementation relevant to real-time generative video or interactive world systems.

Run the supplied example on representative hardware and review every linked licence before production use.

How It Works

  • Uses autoregressive diffusion and an action-oriented mask cache to avoid recomputing unchanged areas during instruction-guided video editing.

What We Like

  • Includes single-GPU inference, long-video rolling attention and a token-pruning configuration with mask visualisation.

Current Limitations

  • The released checkpoint was trained on shorter sequences, so quality may degrade when rolling attention extrapolates far beyond that horizon.

Pricing & Access

  • Repository code is published under Apache-2.0. Confirm separate model, dataset and dependency terms before reuse.
  • No hosted price is inferred. Budget for the documented GPU, storage and setup requirements.

Verification Summary

  • Official repository and licence reviewed on 2026-09-14. Video Runtime has not installed or benchmarked this project.
  • Performance and compatibility statements below are attributed to the maintainers and are not site measurements.
Technical notes & official performance

Official Performance Data

  • The maintainers describe real-time streaming editing, but the inspected README does not provide a universal camera-to-display latency across hardware.

Technical Notes

  • Training scripts use multi-GPU torchrun, while the documented inference path supports a single GPU.

Sources

  1. Official GitHub repository ↗github · accessed 2026-09-14
  2. Code licence ↗github · accessed 2026-09-14

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.