comfy-mecha is a complete model merging node pack for ComfyUI with a focus on low memory footprint.
- compose complex recipes without needing to save dozens of intermediate merges to disk
- merge loras to models
- support for block weights
- and a bunch of other stuff. For more info, see the nodes listing below. See also the readme of the underlying library sd-mecha
Recipe workflows can get much, much more complex than this.
If you are familiar with writing python code, you might be interested in using the sd-mecha library directly for experiments as an alternative to ComfyUI: https://github.com/ljleb/sd-mecha
Assuming you have ComfyUI-Manager installed:
- Open a browser tab on ComfyUI
- Click on the "Manager" button
- Click on "Install Custom Nodes"
- Search for "mecha"
- Install "Mecha Merge Node Pack"
You can also install the node pack manually:
cd custom_nodes
git clone https://github.com/ljleb/comfy-mecha.git
pip install -r comfy-mecha/requirements.txt
Nodes used for merging. They all have Recipe
in their name except for Mecha Merger
.
- nodes ending in
... Mecha Recipe
return a merge recipe Mecha Merger
takes aMECHA_RECIPE
as input, and returns a unet and a text encoderMecha Model Recipe
loads a model as a recipe to be used as input to other recipe nodes. model architecture detection is not yet supported, so please make sure the rightarch
parameter is selected!Mecha Recipe List
takes an arbitrary number of recipes and returns aMECHA_RECIPE_LIST
. It is intended to be used as input to recipe nodes that accept an arbitrary number of recipes as input, i.e. thebounds
input ofClip Mecha Recipe
Mecha Custom Code Recipe
is a very experimental node for custom code and might be removed eventually. It is hard to create recipes and debug with it. I'd advise against using it and instead registering a custom merge method using the sd-mecha library directly
Nodes used to specify hyper(parameters) to merge methods. For example, Weighted Sum Mecha Recipe
has a hyper input alpha
with a default value of 0.5
.
Blocks Mecha Hyper
can specify a different hyper for each block of the models to be merged (AKA "merge block weighted" or "MBW")Float Mecha Hyper
specifies the same float for all blocks of the models to be merged
To add custom merge nodes, you can add python scripts that make use of the mecha extension API under the mecha_extensions
directory.
The node pack will run all scripts placed there before creating the comfy nodes.
Currently, the documentation for the mecha extension API is under construction. For now, to get more information, you can either take a look at the custom merge method example, open a discussion post to ask questions, or join the discord server.