EDITORIAL VIEW
Editor's Verdict
Useful as a broadcast-pipeline reference, not proof that fresh video is generated as fast as it plays.
The author separates clip production from playback and reuses the clip pool to fill airtime.
How It Works
- Chat prompts pass through a language model and local GPU workers; a separate process streams the completed clip pool.
What We Like
- Generation and playback can restart separately, limiting disruption from a failed worker.
Current Limitations
- The documented setup uses two RTX 5090 GPUs. No explicit repository licence was found in the inspected root; public visibility alone does not grant open-source rights.
- We did not verify the linked YouTube broadcast's current uptime or reproduce the hardware results.
Pricing & Access
- Budget for GPUs, electricity and any language-model service. Check code and model permissions before reuse.
Verification Summary
- Official public sources reviewed on 2026-09-05. This is not a hands-on test or uptime guarantee; no paid generation was performed.
Technical notes & official performance
Official Performance Data
- No comparable end-to-end performance measurement was verified for this listing.
Technical Notes
- The implementation uses ComfyUI, a shared file pool and RTMP delivery. Author-reported generation throughput is not a site benchmark.
Sources
- Author repository and architecture ↗github · accessed 2026-09-05
FROM PEOPLE WHO HAVE TRIED IT
User experiences
Reviewed community contributions, kept separate from our research and hands-on tests.
No published experiences yet. Tried this project? Share what worked and what didn’t.
Sharing experiences will open once email sign-in and submission protection are ready. You can still send a correction.
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.
A related project selected in this entry’s research.Public repository; self-hosted setup and compatible GPU required
An endless AI-generated television channel where viewers write what should air next.
Related online experience linked in this entry’s research.Public page with a human-verification step for interaction
A hosted text-to-video and image-to-video model with 480P, 768P, 2K, and 4K price records.
Related model reference for further research; not a confirmed integration.Developer APIRead how official-source and hands-on records stay separate in our Methodology.