# multimodal-art-projection/YuE

YuE: Open Full-song Music Generation Foundation Model, something similar to Suno.ai but open

Repository: https://github.com/multimodal-art-projection/YuE
Canonical: https://ross.abutalabs.com/products/yue
Homepage: https://map-yue.github.io
Language: Python
License: Apache-2.0
License Family: permissive
Topics: foundation-models, music-generation, huggingface, llama, audio-generation, voice-cloning, llms, style-transfers, ai, deep-learning, gpt
Last push: 2025-06-04T13:08:48+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 25, release rhythm 35, longevity 41
- inputs: {"age_days": 587, "days_push": 455, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 6403, forks 759 (observed 2026-08-28T04:09:43.151313+00:00)

## What it is
YuE is a family of open-source foundation models based on the LLaMA2 architecture that generate full songs (up to five minutes) with vocals and accompaniment from lyrics. It supports multiple languages, style transfer, music continuation, and LoRA fine-tuning.

## Use cases
- generate a full song from lyrics
- open-source alternative to Suno.ai
- convert a song's style while keeping the accompaniment
- continue or extend an existing piece of music
- fine-tune a music generation model on custom data
- generate songs in English, Chinese, Japanese, or Korean

## When to choose
- you need self-hosted, license-friendly full-song generation with vocals
- you want to fine-tune or research music generation models
- you need multilingual lyrics-to-song generation

## When to avoid
- you lack a GPU (models are 7B-scale and VRAM-hungry)
- you only need instrumental background music or short audio clips
- you want a polished end-user product rather than model weights and scripts

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, audio-processing, llm-inference, tts
- domain: artificial-intelligence, deep-learning, large-language-models, media
- platform: python, cross-platform
- tags: music-generation, lyrics2song, foundation-model, suno-alternative, voice-cloning, style-transfer, llama, huggingface, audio, gpu

## Member repositories
- multimodal-art-projection/YuE (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:43.151313+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:44:57.712697+00:00, confidence not recorded.
  - readme: https://github.com/multimodal-art-projection/YuE (fetched 2026-08-28T04:09:43.151313+00:00, sha c369b31303c5)
  - homepage: https://map-yue.github.io (fetched 2026-08-29T08:41:50.718612+00:00, sha 7a2bf2993c72)
- Data as of 2026-08-30T08:39:29.467469+00:00.