The node is compatible with LoRA models based on transformers and PEFT, such as those supported in ComfyUI workflows (Qwen-Image, Wan Video, SD, SDXL, Illus. Flux)

A ComfyUI custom node for merging 2 or 3 LoRA models using various merging methods with compatibility checking.

This node is related to this article.

Features

• Multi-LoRA Support: Merge 2 or 3 LoRA models in a single operation

• Multiple Merge Methods:

  • Linear merge (overrides weighted average method)

  • Concatenation merge (preserves LoRA structure)

  • Weighted average merge (normalized strengths)

• Compatibility Checking: Validates LoRA compatibility before merging

• Flexible Strengths: Individual strength control for each LoRA

Usage

1. Two LoRA Merge: Set lora_name3 to "None" and use only the first two LoRAs

2. Three LoRA Merge: Select actual LoRA files for all three inputs

3. Strength Values:

   • Positive values add the LoRA effect

   • Negative values subtract the LoRA effect (try small values -0.1 to -0.33 )

   • Zero ignores the LoRA

4. Merge Methods:

   • linear: Fast direct addition (recommended for most use cases)

   • concatenation: Preserves internal LoRA structure (more sophisticated)

   • weighted_average: Normalizes strengths to prevent overpowering

If you have the psych for dealing with GitHub, feel free to publish it and add it to the ComfyUI custom node repository