WanSong: 5-Minute Long Song Generation Model
Wan-AI · hf · 2026-07-17
WanSong v1.0: A Pure Diffusion Model for Long Song Generation
Wan-AI released the technical report for WanSong v1.0, aiming for "commercial-grade" long-form song generation. The authors believe the current difficulty in music generation lies in achieving high fidelity, long duration, and controllability/customization simultaneously.
Model Features
- Adopts a pure diffusion approach, rather than AR or cascaded multi-stage pipelines
- Can directly generate high-fidelity, multilingual songs up to 5 minutes long
- A single generation outputs dual tracks: vocals + accompaniment
- Supports inference speedup via step-distillation
- Provides highly efficient fine-tuning and customization paths for downstream editing tasks
This report focuses not on isolated demos, but on pushing the efficiency, quality, and controllability of long-form music generation forward together.
Related event: Wan Team Releases WanSong Music Generation Model(2 posts)→
More from Multimodal
- Midjourney style code share: --sref 2912175708 — tisch_eins · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11
- MiniMax H3 MAX nails cooking anime clips: 15-second curry demo with prompts shared — Hailuo_AI · 2026-09-11
- MiniMax Music Production Toolkit 2.5 for ComfyUI adds full mastering chain — Vivid_Promise1700 · 2026-09-11
- New Node Finder for ComfyUI ranks fresh nodes by star velocity and recency — Luke2642 · 2026-09-11
- Using a finisher move on one mosquito with MiniMax H3 MAX — the bug survives — Hailuo_AI · 2026-09-11