Save 4 hours! We auto-setup your workflow! Free!

Drop your workflow.json — we handle every dependency, custom node, and model. Just open the link and run.

Auto-Setup Workflow Json (Free) Now!
ComfyUI > Nodes > ComfyUI-FL-YuE2 > FL_YuE2_LoadLoRA

ComfyUI Node: FL_YuE2_LoadLoRA

Class Name

FL_YuE2_LoadLoRA

Category
FL YuE2
Author
filliptm (Account age: 2551days)
Extension
ComfyUI-FL-YuE2
Latest Updated
2026-09-17
Github Stars
0.13K

How to Install ComfyUI-FL-YuE2

Install this extension via the ComfyUI Manager by searching for ComfyUI-FL-YuE2
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI-FL-YuE2 in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

FL_YuE2_LoadLoRA Description

Facilitates loading LoRA models for YuE2 music generation, enhancing adaptability and performance through customizable adapters.

FL_YuE2_LoadLoRA:

The FL_YuE2_LoadLoRA node is designed to facilitate the loading of LoRA (Low-Rank Adaptation) models specifically tailored for the YuE2 music generation framework. This node plays a crucial role in enhancing the adaptability and performance of the YuE2 model by allowing you to integrate additional LoRA adapters that can modify the model's behavior. By leveraging these adapters, you can fine-tune the model's output to better suit specific musical styles or requirements. The node is particularly beneficial for users who wish to experiment with different acoustic and autoregressive (AR) configurations, providing a flexible approach to model customization. The primary goal of this node is to streamline the process of loading and applying LoRA adapters, ensuring that the YuE2 model can be easily adapted to various musical contexts without requiring extensive technical knowledge.

FL_YuE2_LoadLoRA Input Parameters:

music_model

This parameter represents the base YuE2 model that you wish to enhance with LoRA adapters. It is essential for defining the core model that will be modified by the selected adapters. The music model serves as the foundation upon which the LoRA modifications are applied, allowing for customized output based on the chosen adapters.

ar_adapter

The ar_adapter parameter allows you to select a specific AR LoRA adapter from a list of available options. This adapter is responsible for modifying the autoregressive components of the YuE2 model. The parameter includes a tooltip that indicates the location of saved AR LoRA files, typically under models/loras/YuE2. The default option is "none," which means no adapter is applied unless specified. This parameter is crucial for users who want to experiment with different AR configurations to achieve desired musical effects.

ar_strength

This parameter controls the strength of the AR adapter's influence on the YuE2 model. It is a floating-point value ranging from 0 to 2, with a default value of 1.0. A value of 0 disables the adapter's effect, while a value of 1 applies the trained weights at full strength. Adjusting this parameter allows you to fine-tune the impact of the AR adapter on the model's output, providing flexibility in achieving the desired musical style.

adapter (optional)

The adapter parameter is optional and allows you to specify additional YuE2 adapters that can be applied to the model. These adapters can further modify the model's behavior, providing additional customization options. If specified, the adapter takes precedence over the ar_adapter selection, allowing for more granular control over the model's output.

nar_strength (optional)

This optional parameter controls the strength of the Non-Autoregressive (NAR) adapter's influence on the YuE2 model. It is a floating-point value ranging from 0 to 2, with a default value of 1.0. A value of 0 disables the entire NAR adapter, including its pretrained component, while a value of 1 applies it fully. This parameter does not affect the AR strength, allowing you to independently adjust the NAR adapter's impact on the model's output.

FL_YuE2_LoadLoRA Output Parameters:

YUE2_MODEL

The output YUE2_MODEL represents the modified YuE2 model after the selected LoRA adapters have been applied. This model incorporates the changes specified by the AR and NAR adapters, allowing for customized musical output. The modified model can be used in subsequent nodes to generate music that reflects the applied adaptations.

FL_YuE2_LoadLoRA Usage Tips:

  • Ensure that the ar_adapter parameter is set to a valid AR LoRA file to avoid errors and achieve the desired model modifications.
  • Experiment with different ar_strength and nar_strength values to find the optimal balance for your specific musical style or project requirements.

FL_YuE2_LoadLoRA Common Errors and Solutions:

ValueError: Select an AR LoRA adapter

  • Explanation: This error occurs when the selected adapter is not a valid AR LoRA file.
  • Solution: Ensure that the ar_adapter parameter is set to a valid AR LoRA file with the correct metadata indicating it is an AR adapter.

YuE2 produced non-finite audio

  • Explanation: This error indicates that the model produced audio with non-finite values, which can occur if the model configuration is incorrect.
  • Solution: Verify that the input parameters are correctly set and that the selected adapters are compatible with the base YuE2 model. Adjust the ar_strength and nar_strength parameters if necessary.

FL_YuE2_LoadLoRA Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI-FL-YuE2
RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

FL_YuE2_LoadLoRA