Published by Video Runtime · Source check 2026-09-05 · Evidence method · Suggest a correction
EDITORIALLY VERIFIED PRODUCT INFORMATION
About StreamV2V
Study streaming video-to-video stylization with feature banks that reuse information from earlier frames. Reuses past-frame features to improve consistency during streaming video transformation, building on StreamDiffusion.
Key features
Provides a research implementation for experimenting with continuous, prompt-driven video stylization.
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
Reuses past-frame features to improve consistency during streaming video transformation, building on StreamDiffusion.
Pricing
UT Austin Research License — restricted use; compute costs extra Repository code: UT Austin Research License — restricted use. 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
Source is available under a research licence, not unrestricted open source. Commercial use and redistribution require separate permission; read the linked licence.
EDITORIAL VIEW
Editor's Verdict
Consider StreamV2V 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
- Reuses past-frame features to improve consistency during streaming video transformation, building on StreamDiffusion.
What We Like
- Provides a research implementation for experimenting with continuous, prompt-driven video stylization.
Current Limitations
- Source is available under a research licence, not unrestricted open source. Commercial use and redistribution require separate permission; read the linked licence.
Pricing & Access
- Repository code: UT Austin Research License — restricted use. 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
- The authors describe real-time translation on an RTX 4090. This has not been reproduced by Video Runtime or measured over a public network.
Technical Notes
- Uses Stable Diffusion and LCM-based components; downloaded models and adapters retain their own terms.
Sources
- Official GitHub repository ↗github · accessed 2026-09-05
- Code licence ↗github · 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
CONTINUE EXPLORING
Related projects & models
Selected by research links and category, not by popularity.
Run ComfyUI workflows on live video streams, with a browser interface and WebRTC transport.
Another live transformation option in this section.Public repository; self-hosted setup and compatible GPU requiredA source-available tool for running interactive generative-video pipelines, with a non-commercial alpha licence.
Another live transformation option in this section.Source-available, non-commercial; local or cloud GPU setup requiredTransform webcam and screen frames with an accelerated diffusion pipeline for interactive visuals.
Another live transformation option in this section.Public repository; self-hosted setup and compatible GPU required
A hosted real-time video-to-video editing model with live prompts, references and SDK sessions.
Another live transformation option in this section.Developer platform; account, API key, client token and usage credits requiredRead how official-source and hands-on records stay separate in our Methodology.