快讯6 条
快讯3 条 · 可滚动
本站于 2026-10-19 补核;官方发布日期为 2026-10-17。

出处:DeepSeek 官方文档 · 更新日志官方

本站于 2026-10-19 补核;官方发布日期为 2026-10-14。

出处:xAI · API Release Notes官方

本站于 2026-10-19 补核;官方发布日期为 2026-10-13。

出处:Gemini API · Release notes官方

开源项目解析

YuE2

当前默认分支为 YuE2,联合符号乐谱与音频生成完整歌曲;旧 YuE 代码与许可保留在 YuE-v1 分支。

整首带人声Apache-2.0
代码 Apache-2.0;权重 CC BY-NC-4.0+创作者附加许可 有条件商用★ 12.3k 589 星/月最后更新 2026-10-06 · 距核验日 0 个月仓库 ↗

许可证附加条件:2026-10-10 核 README:代码、技能和文档 Apache-2.0;权重另有 MODEL_LICENSE,公司商用需联系授权。旧 YuE-v1 的许可不能套到 YuE2。

读懂层

2 张 · 架构图 / 时序图

架构图东西怎么摆

License Structure

Creates

Processes

Apache License 2.0

YuE Codebase

YuE Models

Generated Content

DeepWiki · 抓取 2026-08-17 · 核验 2026-08-17

时序图一次调用经过什么
"Stage 1 Output""CodecManipulator""Stage 1 Model""MMTokenizer""Input Preparation"alt[Using Audio Prompt (ICL mode)]loop[For each lyric segment]Genre tags & lyricsEncode audio promptAdd audio tokens to promptTokenized promptGenerate audio tokensOutput raw token sequenceExtract & separate vocal/instrumentalSave vocal tokens (.npy)Save instrumental tokens (.npy)

DeepWiki · 抓取 2026-08-17 · 核验 2026-08-17

它管哪几个决定

音乐与音效描述生成音乐
0/10 家有官方说法

自持能力

动手层

还没做。装它要过哪几关、改哪个文件能改什么、坑在代码哪一处 —— 这三项要读源码,尚未完成。

教程

没找到官方口径的教程 —— 官方只给了 README。

项目自述

以下是仓库 README 的开头部分(原文引用,抓取 2026-08-17)。读全文 ↗

> Looking for the original YuE? Its code, documentation, and license are preserved on the YuE-v1 branch.

YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality

Compose in symbols. Create in sound.

  📄 arXiv ·
  PDF ·
  🎧 Demos ·
  🚀 Try online (free) ·
  🗳️ Music Arena ·
  📰 News ·
  🤗 YuE2 ·
  🚀 Quick start ·
  🤖 Agent skill ·
  📊 Benchmarks ·
  🤗 MERT2 ·
  🤗 SheetSage2 ·
  🤗 WSB ·
  📦 Release ·

  All languages · September 14, 2026

  Global: September 17, 2026 · Text-to-Audio: September 20, 2026

YuE2 brings frontier song quality to music generation with an editable composition. Give it lyrics and a style prompt: it writes a melody-and-chord plan, then realizes that plan as a complete song with vocals and accompaniment.

> 🎧 YuE2 needs your ears
>
> We're running a public blind listening study comparing YuE2 with leading proprietary music generation systems. Hear anonymous clips and choose A, B, or a tie.
>
> Listen & vote → · No account needed; headphones recommended.

- Frontier quality. YuE2 is competitive with Suno v5/v6 on WildSongBench. YuE2 (best-of-8) achieves 6.9632 SongBench Avg, the highest observed mean among all evaluated settings.
- White-box music generation through symbolic planning. Read, play, and change the composition before rendering it. Melody and chords become explicit controls that a person or an agent can inspect and edit.
- Zero-shot covers and agentic editing. Reimagine a transcribed song in a new style, or refine a song through a conversation about its score, arrangement, and lyrics—all with the same generation checkpoint.

*192 WildSongBench prompts. Both YuE2 settings use symbolic planning. Bo8 = best-of-8. The axes are normalized comparison indices; bubble area represents AudioBox production quality. Scores and evaluation protocol. Vector PDF · SVG.*

News

- 📄 October 6, 2026 — SheetSage2 on arXiv. Read the paper and use the BibTeX citation.

- 📄 October 2, 2026 — SheetSage2 technical report. The SheetSage2 report describes the transcription model used for covers and score editing: MIDI-derived synthetic supervision, structured decoding, and autoregressive distillation, with evaluations on eight benchmark collections.

- 📄 September 29, 2026 — YuE2 on arXiv. Read the paper and use the BibTeX citation.

- 📄 September 26, 2026 — YuE2 technical report. Our technical report is now available, with the full model and training methods, automatic and expert listening results, and evaluations of score editing and zero-shot covers.
- 🎹 September 25, 2026 — Instrumental generation and covers. The yue2-music agent skill now turns a simple description, ABC score, or reference recording into instrumental music. YuE2 writes the score by default; the skill moves the vocal melody into the instrumental part before rendering. Recommended agent: GPT-6 Astra. Download the updated skill →
- 🚀 Try YuE2 online for free. Create a song in your browser with the NOIZ-hosted demo →. No installation required.
- ⚡ YuE2-Turbo. NOIZ's inference and serving toolkit → accelerates YuE2 and supports concurrent requests.
- 🎛️ ComfyUI. YuE2 has native nodes and an official text-to-music workflow →.
- 🎬 Mae

……(后略,见原文)

判断

优势

  • 整首带人声,做主题曲这类需求对得上
  • 代码与文档开放,权重许可另行规定;可在本机生成并保留乐谱、音频及生成配置。

局限

  • 公司商用权重需联系授权;学术研究与教育按非商用条款使用。
  • 带人声意味着推理更重
  • 游戏里大部分场合要的是纯伴奏,人声反而是负担

不适用

要循环播放的背景音乐 —— 带人声的整曲不适合长时间循环。

同管这些决定的其它项目

github README + DeepWiki · 核验 2026-10-19 | 判断栏可报错。