Generating K-Pop music videos with a Claude Music Video skill, no MCP needed
AIandDesign · x · 2026-10-29
AIandDesign shares another music video made with his Claude Music Video skill, this time for virtual K-Pop group V3X. The new approach skips MCP: the skill outputs prompts plus "dark videos" (audio-only clips for lipsync in SeeDance), which are fed to Dreamina with reference images (one for the characters, one for the environment); rendered clips go into the working directory and the skill handles the rest — a replicable Claude-skill-plus-video-model MV pipeline.
Related event: Claude Music Video skill auto-generates full K-pop MVs from a song(2 posts)→
More from coding & agent
- Dynamic workflows shine at ~10 subagents: editable JS gives full control over runs — daniel_mac8 · 2026-10-29
- AI writes, tests and reviews the code — and engineers are losing understanding of their own systems — julianweisser · 2026-10-29
- Coding agents burn 95-99% cached tokens per benchmark task, token usage chart shows — AccBalanced · 2026-10-29
- Open-source screen recorder Cap v0.6.2 ships 89% faster share links, 2.8x exports — JosephJacks_ · 2026-10-29
- Professor builds videos with Codex and Blender, where creative goals resist alignment — CSProfKGD · 2026-10-29
- Grok voice agent breaks down, sparking rant against renting other people's agent harnesses — alexcovo_eth · 2026-10-29