Paper Detail

WanSong v1.0 Technical Report

Binghui Chen, Pandeng Li, Yu Liu, Jingren Zhou

huggingface Score 5.4

Published 2026-07-16 · First seen 2026-07-17

General AI

Abstract

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{chen2026wansong,
  title = {WanSong v1.0 Technical Report},
  author = {Binghui Chen and Pandeng Li and Yu Liu and Jingren Zhou},
  year = {2026},
  abstract = {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 (\textbackslash{}eg, AR followed by diffusion), WanSong is a pure diffusion-based model that directly generate},
  url = {https://huggingface.co/papers/2607.14749},
  keywords = {huggingface daily},
  eprint = {2607.14749},
  archiveprefix = {arXiv},
}

Metadata

{}