Lip sync AI music video. Fully automatic operation with a system that connects ACE-Step, Krea 2, LTX 2.5, and Qwen 3.8 27B.
Two clips were corrected and recombined. RTX 5090 + DGX Spark
The "tell me without telling me" apocalypse onset
Military grade intervention? In 5-10 years time? It's here now - thx to a reckless "frontier lab push" vs "open weights self-defense-idea" loop - and they don't tell us. Ability to..: 1. ..recursively self-improve 2. ..set
Made this full video locally on rtx 5090, using minimax h3
Took 1 hour of gpu time and electricity qwen 3.8 for scripts/screenplay qwen edit for consistent images qwen minimax h3 for image to video china winning
Qwen 3.8-27B might be the best free local AI model ever released.
6 months ago this power was locked in the cloud. Now it runs on a MacBook. Here's the setup: → It performs at Claude Opus 4.6 level. For free → Download it with one click in Ollama or LM Studio → On Mac,
You have reached the end of the archive
All of qwen38