What problem does it solve? Generating complete songs with vocals from text requires either paid services like Suno or complex local model setups. This Skill guides you through installing, patching, and running HeartMuLa, an open-source music generation model family, so you can produce songs locally from lyrics and style tags. ## Core Features & Use Cases - Lyrics-to-Song Generation: Produce full MP3 songs (48kHz stereo) conditioned on bracketed lyrics and comma-separated style tags using the 3B/7B HeartMuLa models. - VRAM-Constrained Operation: Run on GPUs with as little as 8GB VRAM using lazy loading, or split models across multiple GPUs. - Dependency & Source Patching: Includes fixes for transformers 5.x RoPE cache issues and HeartCodec checkpoint loading mismatches. - Use Case: A musician wants a local, offline Suno alternative. They write lyrics with [Verse]/[Chorus] tags, specify tags like "piano,happy,wedding", and generate a 4-minute song in about 4 minutes on a single GPU. ## Quick Start Ask the AI to install HeartMuLa and generate a song from your lyrics file and style tags using the 3B model with lazy loading enabled.
