Open-source music model YuE2 runs locally on 4.5GB VRAM, outputs 48kHz full songs
cocktailpeanut · x · 2026-09-17
A French developer shared hands-on experience with YuE2, an open-source music generation model that produces 48kHz stereo audio and runs locally with just 4.5GB of VRAM, installable in one click via Wan2GP in Pinokio.
- He fed the model his 30-year-old composition plus lyrics and got multiple style reinterpretations he found "stunning," then had his AI agent Hermes create a matching music video.
- Code and weights are public; no hosted service required.
- Limitation: no text tags yet to control duration diversity, worked around via comping.
- A companion article explains how the 48kHz output shapes perceived quality.
More from Multimodal
- Fable 5.5 creates 66-second animated short entirely with self-written code, no image models — oran_ge · 2026-11-02
- LTX-2.5 trains 'surgically precise' LoRAs with rare subject generalization, says user — Aivan-Studios · 2026-11-02
- Synthesia now creates videos inside ChatGPT and Claude chats — synthesiaIO · 2026-11-02
- AI-generated 'mechanic rug' optical illusion goes viral: a handyman living under the coffee table — Delahuntagram · 2026-11-02
- Keeping one face on-model across 16 comic pages with Gemini: what held and what drifted — Money_Parfait8955 · 2026-11-02
- Pika's pika-h3-flex Space Trends on Hugging Face — Pika-Labs · 2026-11-02