ModelMergeSD1 - ComfyUI Built-in Node Documentation - ComfyUI

The ModelMergeSD1 node blends two Stable Diffusion 1.x models together by adjusting how much each model component contributes to the result. It gives individual control over the time embedding, label embedding, and every input, middle, and output block, allowing fine-tuned model merging for specific use cases.

Inputs

Parameter	Description	Data Type	Required	Range
`model1`	The first model to merge	MODEL	Yes	-
`model2`	The second model to merge	MODEL	Yes	-
`time_embed.`	Time embedding layer blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`label_emb.`	Label embedding layer blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`input_blocks.0.`	Input block 0 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`input_blocks.1.`	Input block 1 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`input_blocks.2.`	Input block 2 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`input_blocks.3.`	Input block 3 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`input_blocks.4.`	Input block 4 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`input_blocks.5.`	Input block 5 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`input_blocks.6.`	Input block 6 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`input_blocks.7.`	Input block 7 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`input_blocks.8.`	Input block 8 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`input_blocks.9.`	Input block 9 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`input_blocks.10.`	Input block 10 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`input_blocks.11.`	Input block 11 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`middle_block.0.`	Middle block 0 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`middle_block.1.`	Middle block 1 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`middle_block.2.`	Middle block 2 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`output_blocks.0.`	Output block 0 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`output_blocks.1.`	Output block 1 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`output_blocks.2.`	Output block 2 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`output_blocks.3.`	Output block 3 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`output_blocks.4.`	Output block 4 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`output_blocks.5.`	Output block 5 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`output_blocks.6.`	Output block 6 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`output_blocks.7.`	Output block 7 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`output_blocks.8.`	Output block 8 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`output_blocks.9.`	Output block 9 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`output_blocks.10.`	Output block 10 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`output_blocks.11.`	Output block 11 blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)
`out.`	Output layer blending weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0 (step: 0.01)

All blending weights accept values from 0.0 to 1.0 and are set to 1.0 by default, meaning each component of the first model is fully used unless adjusted.

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): b9d53f126139412fbd8b21be72e1dcdb02736519ab4dc9e28c7840d69acb7c87