ModelMergeSD3_2B - ComfyUI Built-in Node Documentation

The ModelMergeSD32B node allows you to merge two Stable Diffusion 3 2B models by blending their components with adjustable weights.

The ModelMergeSD3_2B node allows you to merge two Stable Diffusion 3 2B models by blending their components with adjustable weights. It provides individual control over embedding layers, transformer blocks, and the final layer, enabling fine-tuned combinations of two models.

Inputs

Parameter	Description	Data Type	Required	Range
model1	The first model to merge	MODEL	Yes	-
model2	The second model to merge	MODEL	Yes	-
pos_embed.	Position embedding interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
x_embedder.	Input embedding interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
context_embedder.	Context embedding interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
y_embedder.	Y embedding interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
t_embedder.	Time embedding interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.0.	Joint block 0 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.1.	Joint block 1 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.2.	Joint block 2 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.3.	Joint block 3 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.4.	Joint block 4 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.5.	Joint block 5 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.6.	Joint block 6 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.7.	Joint block 7 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.8.	Joint block 8 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.9.	Joint block 9 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.10.	Joint block 10 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.11.	Joint block 11 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.12.	Joint block 12 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.13.	Joint block 13 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.14.	Joint block 14 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.15.	Joint block 15 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.16.	Joint block 16 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.17.	Joint block 17 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.18.	Joint block 18 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.19.	Joint block 19 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.20.	Joint block 20 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.21.	Joint block 21 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.22.	Joint block 22 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
joint_blocks.23.	Joint block 23 interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0
final_layer.	Final layer interpolation weight (default: 1.0)	FLOAT	Yes	0.0 - 1.0

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): db27b10ade457933f6225218bb806aafcf9fc4478cac85b1623a75d110103529