Turns written dream descriptions into videos through an automated pipeline that connects to the JiMeng platform. You paste in dream journal entries or spoken dream recollections, it generates cinematic prompts following strict realism rules (no anime aesthetics, hardcore photography terminology, fish-eye lenses for spatial distortion), then spawns a worker that handles the browser automation, uploads reference images if your dream mentions company environments, monitors generation progress, and downloads the final 15-second video. The prompt engineering is opinionated and detailed, enforcing things like POV perspectives, no overlaid text, ethnicity tagging for background characters, and VHS-style glitch effects at frame edges. Setup requires Python 3.10+, Playwright, and a one-time QR code login to the platform.
npx skills add https://github.com/mediastormdev/dream-to-video-skill --skill dream-to-video