Maestro v2.2.0 ships open-source YuE2 music model with local training on Pinokio
cocktailpeanut · x · 2026-09-17
Maestro v2.2.0 on Pinokio adds the open-weight YuE2 3B music model as its default — claimed to rival Suno v5 while running free and low-VRAM locally. It generates 48 kHz stereo tracks with optional composition planning, ABC scores, and covers. A new experimental 'My Music' feature lets users train personal style adapters from their own recordings and lyrics. The release also unifies AI prompt enhancement across models and improves H3 prompt writing for camera direction, first-frame continuity, and multi-window timing, with Director gaining clip limits, GPU controls, and full-song timing.
More from Multimodal
- HunyuanVideo 1.5 Outputs Black Video: Only Certain Frame Lengths Render — Big-Maybe-2228 · 2026-09-17
- QuiverAI launches Arrow 2, its most advanced model for editable vector graphics — stuffyokodraws · 2026-09-17
- SuperSplat now shows splat counts for your 3D scenes — willeastcott · 2026-09-17
- ai-toolkit, the open-source LoRA trainer, lands on Pinokio for 1-click installs — cocktailpeanut · 2026-09-17
- Spotify's AI Persona Badge Targets Photorealistic Identities, Not Royalties — mixtapedmonk · 2026-09-17
- Blender + AI modeling tip: design parts separately and keep everything assemblable — kevinkern · 2026-09-17