WanSong v1.0 Technical Report

Hugging Face Daily Papers Papers

Summary

WanSong is a pure diffusion-based music generation model that directly produces high-fidelity, multilingual songs up to 5 minutes long with dual stems (vocals and background music) in a single run, addressing challenges in efficient generation, long-form audio, and controllability.

Music generation foundation models have recently attracted significant industry attention. However, achieving efficient generation and high-fidelity long-form audio while supporting controllability remains challenging. To address these needs, we present WanSong, a simple yet powerful approach for long-form, commercial-grade song generation. Unlike autoregressive (AR) and cascaded multi-stage pipelines (\eg, AR followed by diffusion), WanSong is a pure diffusion-based model that directly generates high-fidelity, multilingual songs up to 5 minutes and outputs dual stems (vocals and background music) in a single run. In addition, our diffusion framework enables faster inference through step-distillation, and offers an efficient pathway for fine-tuning and customization to support downstream editing tasks.
Original Article
View Cached Full Text

Cached at: 07/20/26, 09:43 AM

Paper page - WanSong v1.0 Technical Report

Source: https://huggingface.co/papers/2607.14749

Abstract

Musicgenerationfoundationmodelshaverecentlyattractedsignificantindustryattention.However,achievingefficientgenerationandhigh-fidelitylong-formaudiowhilesupportingcontrollabilityremainschallenging.Toaddresstheseneeds,wepresentWanSong,asimpleyetpowerfulapproachforlong-form,commercial-gradesonggeneration.Unlikeautoregressive(AR)andcascadedmulti-stagepipelines(\eg,ARfollowedbydiffusion),WanSongisapurediffusion-basedmodelthatdirectlygenerateshigh-fidelity,multilingualsongsupto5minutesandoutputsdualstems(vocalsandbackgroundmusic)inasinglerun.Inaddition,ourdiffusionframeworkenablesfasterinferencethroughstep-distillation,andoffersanefficientpathwayforfine-tuningandcustomizationtosupportdownstreameditingtasks.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2607\.14749

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.14749 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.14749 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.14749 in a Space README.md to link it from this page.

Collections including this paper3

Similar Articles

Qwen-Music Technical Report

Hugging Face Daily Papers

Qwen-Music is a music generation model that produces high-fidelity songs with vocals, supporting text-to-music and cover song generation. It uses a novel Melody-Chain-of-Thought mechanism and achieves state-of-the-art results on 13 of 16 objective metrics.