TESIGN
SAVED

EN · KO

  1. TESIGN / RADAR
  2. YuE2

YuE2

Songs from lyrics and a style prompt

WHO USES ITVideo maker · Music researcher · ML engineer

Install to use

Generates music, makes zero-shot covers and edits parts of a track.

★ 9k▲ +381 / 7dDaily star increases over 14 days. Hollow bars mean no data. The last day may be partial.2026-09-03 no data2026-09-04 no data2026-09-05 no data2026-09-06 no data2026-09-07 no data2026-09-08 no data2026-09-09 no data2026-09-10 +222026-09-11 +802026-09-12 +622026-09-13 +732026-09-14 +132026-09-15 +782026-09-16 +53largest one-day increase in the 14 days+80last 14 days · stars per dayhollow = no data

8,971 stars · checked on GitHub GitHub check 30 h late · incl. +62 observed via GH Archive since then · 7-day +381 observed via GH Archive (as of )

RANKS Rising this week #20 MEDIA #13

TESIGN TAKE

Planning a song as an editable score, then regenerating from the edit, sets it apart from one-shot generators.

RUN

AT A GLANCE

LICENSE
Apache-2.0
USAGE
Commercial use, redistribution OK. Keep notices; mark changes.
LANGUAGE
Python
PLATFORM
linux
ACTIVITY
last commit 2 days ago () · latest release yue2-v0.1.6 () · 1 release
COMMUNITY
9 contributors · 25 open issues (incl. PRs) · made by: an organization
SOURCES
GitHub
OPEN SOURCE
YES
FIRST SEEN
CATEGORY
AI · MEDIA

A summary, not legal advice.

WHY IT MATTERS

Music generators are hard to correct once a track exists; changing one part usually means generating the whole thing again. YuE2 plans the structure symbolically before generating and keeps zero-shot covers and agentic editing inside the same flow. It is written in Python, published under Apache-2.0, and has a demo page. You run the model yourself, so the environment is yours to prepare.

BUILD FROM THIS

  • A production line that makes your own background music for video
  • An experiment that re-sings an existing track in another voice

WHO IT'S FOR

Video maker
wants original background music (non-commercial only)
Music researcher
works with symbolic planning and audio generation
ML engineer
runs a music model on a GPU server

START IN 5 MINUTES

$ git clone https://github.com/multimodal-art-projection/YuE.git
$ cd YuE
$ python3.12 -m venv .venv
$ source .venv/bin/activate
$ python -m pip install .
$ python examples/generate.py --output outputs/first-song

CAVEATS

  • Needs Linux, Python 3.12 and an NVIDIA GPU with 24 GB of VRAM
  • Code is Apache-2.0, but the model weights are CC BY-NC 4.0 (non-commercial)
  • Model files download from Hugging Face on first use

RECEIPT

FIRST SEEN
AT SOURCE
KEPT
STAR DELTA
+55 ★ / 24h
CREATED → FIRST SEEN
598d
WHEN FIRST SEEN
7,449 ★
SOURCES
GitHub

The same facts in machine-readable form — View as Markdown · JSON

SIMILAR TOOLS

Up to five from AI by ★ total: edited entries first, then repository cards; this entry is highlighted. Drawn from the same stored snapshot as the rankings — a comparison, not a recommendation.

IMAGENAME★ TOTAL▲ 7dLICENSEPLATFORMLAST PUSH
ECC README banner: headline 'The operating system for AI agent harnesses', harness chips, and skill, agent and command lists.
eccSkills, memory and security for agents★ 259k▲ +832MITpermissivewindows · macos · linux · cli
Hermes Agent landing: blue background, the headline 'The agent that grows with you' and an engraving-style winged figure.
Hermes AgentSelf-improving personal agent★ 246k▲ +375MITpermissivelinux · macos · windows · android · cli
DeepSeek Harness landing: blue background, the headline 'Everything is a plugin' and a quick-start box with the npx command.
DeepSeek HarnessPlugin agent harness for developers★ 225k▲ +1,356MITpermissiveweb · cli
YuE2 demo site: the headline 'Frontier quality. Music, with a plan.', a models-and-benchmark box and an audio player bar below.
YuE2Songs from lyrics and a style promptTHIS ENTRY★ 9k▲ +381Apache-2.0permissivelinux
mattpocock/skillsCARD★ 261k▲ +872MITpermissive

TIMELINE

  1. Repository created
  2. FIRST SEEN BY TESIGN