Visión general

YuE AI Music Generation for the GPU Poor (by deepmeepbeep) Our model's name is YuE (乐). In Chinese, the word means "music" and "happiness." Some of you may find words that start with Yu hard to pronounce. If so, you can just call it "yeah." We wrote a song with our model's name. YuE is a groundbreaking series of open-source foundation models designed for music generation, specifically for transforming lyrics into full songs (lyrics2song). It can generate a complete song, lasting several minutes, that includes both a catchy vocal track and complementary accompaniment, ensuring a polished and cohesive result. YuE is capable of modeling diverse genres/vocal styles. Below are examples of songs in the pop and metal genres. For more styles, please visit the demo page. NOTE: On first start-up, a number of inference models and libraries will be downloaded to the cache folder. Be patient. It will be up to 30 GB of storage. NOTE: All generated songs remain in the cache folder - even if they have been downloaded through the WebUI. You may manually remove them, if disk space becomes precious.

Requisitos

Nvidia Driver plugin (nVidia Support)

Argumentos en tiempo de ejecución

Interfaz web: http://[IP]:[PORT:7860]/
Red: bridge
Concha: bash
Privilegiado: false
Parámetros adicionales: --gpus all

Configuración de plantillas

WebUIPorttcp

Port for the main portal.

Objetivo: 7860
Por defecto: 7860
Valor: 7860

Cache folderPathrw

Folder where YuEGP stores the downloaded files. Note that this folder will be between 20 - 30 GB big.

Objetivo: /workspace
Por defecto: /mnt/user/appdata/ai-yue-gp
Valor: /mnt/user/appdata/ai-yue-gp

GPU ProfileVariable

1: Fastest model, but requires 16GB or more. 2: Undefined/undocumented. 3: Slower, up to 12GB VRAM. 4: Slowest, but works with less than 10GB.

Objetivo: YUEGP_PROFILE
Por defecto: 3
Valor: 3

CUDA IndexVariable

Index of the GPU being used for the inference.

Objetivo: YUEGP_CUDA_IDX
Por defecto: 0
Valor: 0

Enable Audio PromptVariable

0: Provide input prompt in text form, i.e. describe the style using keywords. 1: Allows you to send one or 2 audio clips as reference for the style.

Objetivo: YUEGP_ENABLE_ICL
Por defecto: 0
Valor: 0

Transformer PatchVariable

0: Run with the original transformers, without deepmeepbeep's optimizations. 1: Apply the patches - may give unintended side effects in certain configurations.

Objetivo: YUEGP_TRANSFORMER_PATCH
Por defecto: 0
Valor: 0

Auto UpdateVariable

0: Don't update automatically. Use the scripts that are bundled. 1: Update and use the latest features / models. But also accept that this may being breaking changes.

Objetivo: YUEGP_AUTO_UPDATE
Por defecto: 0
Valor: 0

Enlaces

Plantilla Ayuda Centro Docker Project

Detalles

Repositorio

olilanz/ai-yue-gp

Registro

https://hub.docker.com/repository/docker/olilanz/ai-yue-gp

Última actualización2025-03-28

Visto por primera vez2025-02-18

Ejecute YuE-GP en Unraid.

YuE-GP se encuentra en Community Apps para Unraid OS. Explore Unraid para crear un servidor doméstico flexible, un NAS o un laboratorio doméstico.

Explore Unraid OS

YuE-GP