Real-time infinite AI video livestream powered by Minimax H3-Max
OdinLovis · x · 2026-08-30
This project implements an 'infinite TV' livestream that generates and broadcasts AI video in real-time based on Twitch chat using Minimax H3-Max and other fast models. The author open-sourced the repo, tracing the evolution from LTX V1 to H3-Max. The architecture includes prompt generation, LTX video synthesis, and RTMP streaming, backed by a React dashboard and deployed on FAL's serverless GPU infrastructure.
More from coding & agent
- 'LLM code is sloppy' rebutted with real ffmpeg code: identical if/else branches in a top library — kingslyj · 2026-10-16
- Office-editing tool calls need file, worktree and unit: lessons from dsh-univer-office — FunDistribution6537 · 2026-10-16
- Architect MD workflow: Gemini one-shot outputs that beat Opus, via 5-lens plan critique — oikk01 · 2026-10-16
- Prove a coding agent actually ran the tests: check artifacts, not approvals — ComprehensiveShake76 · 2026-10-16
- Building an acceptance harness for AI spreadsheet edits: allowlists, recalc checks, idempotency — ukdicha-modakkk · 2026-10-16
- Agent actions need checks outside the model: NVIDIA demos lean on guardrails amid wave of real agent incidents — Creamy-And-Crowded · 2026-10-16