观众主导直播
Infinite TV
新增Open-source, Twitch-chat-driven AI TV — messages become prompts, LTX Video renders clips live, frames stream back over RTMP.
github.com · 收录≠背书 · 2026-09-03 复核
- 运营方
- Community · GitHub (alex-remade)
- 形态
- Twitch chat → LLM prompts → LTX clips → RTMP
- 模型
- LTX Video (local) or LTX 2.3 Fast via fal
- 输出
- RTMP to Twitch or other endpoints
- 开放情况
- Open source · self-host
什么是 Infinite TV?
An open-source pipeline that turns a Twitch chat into a realtime generative show: messages are rewritten by an LLM into contextual prompts, LTX Video generates clips continuously, and the frames are streamed back out over RTMP. It ships 'regular' and 'nightmare' generation modes with a React dashboard, and is the best-documented community reference for the chat-to-LTX streaming loop (the LTX Video engine is listed under Realtime models).
Infinite TV 能做什么
- Turns a Twitch chat into a realtime generative show — messages become the next prompts
- An LLM rewrites raw chat into contextual prompts before generation
- Generates with LTX Video locally, or LTX 2.3 Fast via fal for cloud rendering
- Streams the generated frames back out over RTMP to Twitch or other endpoints
- Ships “regular” and “nightmare” generation modes plus a React dashboard
Infinite TV 适合谁?
- Self-hosting a chat-controlled AI TV channel for your own community
- Studying the chat → LLM → video → RTMP loop that open-source streamers are built on
- Comparing open pipelines against hosted products like fal.live
Infinite TV 的优点与不足
优点
- Fully open source — the entire loop is inspectable and self-hostable
- Well-documented community reference (600+ stars on GitHub)
- Works with local or cloud generation (LTX vs LTX 2.3 Fast via fal)
不足
- A project you run yourself — no hosted channel to just watch
- Quality depends on the live LTX generation and your own moderation of chat
- Latency and stability vary with your GPU/cloud setup
常见问题
What is Infinite TV?
An open-source, Twitch-chat-driven AI TV: chat messages are turned into prompts, LTX Video generates clips, and frames are streamed back over RTMP.
What model does Infinite TV use?
LTX Video (local) or LTX 2.3 Fast served via fal, with an LLM rewriting chat into prompts.
Is Infinite TV free?
The code is free and open source; you pay for whatever GPU or fal credits the generation consumes.
fal.live
“人人皆可导演的 AI 电视”——观看生成式直播,并为“接下来发生什么”投票。基于 fal 运行。fal.live
InfiniteSlop
24/7 由聊天驱动的无限 AI 视频——你发提示词,几秒内便生成并持续播放。作者 Pieter Levels,运行于 fal。infiniteslop.ai
Renoise Live
永不停机的生存直播——四个岛民的命运,由实时聊天决定。renoise.live
SlopTV
Open-source “infinite AI slop generator from YouTube comments” — your live chat becomes clips, streamed back into the same broadcast.github.com