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