An extension for merging LoRAs. Offers a wide range of LoRA merge techniques (including dare) and XY plots. XY plots require efficiency nodes.

LoRA Power-Merger ComfyUI


    KArcher
    Concept: Computes the Karcher mean (also known as the Riemannian barycenter or Fréchet mean) 
    of the input model parameters. This provides a geometrically sound way to average points on a manifold, 
    which is suitable for model weights.

    Use Cases:
    Finding a "central" or "average" model among a set of diverse models in a way that respects the geometry of the weight space
    More robust averaging than simple linear averaging, especially for models far apart in weight space
    Inputs: Takes 2 or more models. No base_model is used.

    Key Parameters:

    max_iter (global): Maximum iterations for the Karcher mean algorithm. Default 10
    tol (global): Convergence tolerance. Default 0.5
    

ComfyUI Node: PM KArcher (Mergekit)

Category

Inputs

Outputs

Extension: LoRA Power-Merger ComfyUI

More nodes in LoRA Power-Merger ComfyUI

Other LoRA PowerMerge/Spherical Interpolation Methods nodes

Run ComfyUI workflows without the setup