ModelMergeCosmosPredict2_14B - ComfyUI Built-in Node Documentation

The ModelMergeCosmosPredict2_14B node merges two AI models by blending their internal components. It gives you precise control over how much each part of the second model influences the final merged result, using adjustable weight values for specific layers and components.

Inputs

Parameter	Description	Data Type	Required	Range
`model1`	The base model to merge with	MODEL	Yes	-
`model2`	The secondary model to merge into the base model	MODEL	Yes	-
`pos_embedder.`	Position embedder blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`x_embedder.`	Input embedder blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`t_embedder.`	Time embedder blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`t_embedding_norm.`	Time embedding normalization blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.0.`	Block 0 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.1.`	Block 1 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.2.`	Block 2 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.3.`	Block 3 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.4.`	Block 4 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.5.`	Block 5 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.6.`	Block 6 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.7.`	Block 7 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.8.`	Block 8 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.9.`	Block 9 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.10.`	Block 10 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.11.`	Block 11 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.12.`	Block 12 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.13.`	Block 13 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.14.`	Block 14 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.15.`	Block 15 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.16.`	Block 16 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.17.`	Block 17 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.18.`	Block 18 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.19.`	Block 19 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.20.`	Block 20 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.21.`	Block 21 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.22.`	Block 22 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.23.`	Block 23 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.24.`	Block 24 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.25.`	Block 25 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.26.`	Block 26 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.27.`	Block 27 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.28.`	Block 28 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.29.`	Block 29 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.30.`	Block 30 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.31.`	Block 31 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.32.`	Block 32 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.33.`	Block 33 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.34.`	Block 34 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`blocks.35.`	Block 35 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
`final_layer.`	Final layer blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0

Note: All blending weight parameters accept values between 0.0 and 1.0, where 0.0 means no contribution from model2 and 1.0 means full contribution from model2 for that specific component.

Outputs

Output Name	Description	Data Type
`model`	The merged model combining features from both input models	MODEL

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): 5e72608391bc47c2610c93fda19e6e12a1695f95f6135a08efe97e3d400acf84

​Inputs

​Outputs

Inputs

Outputs