Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.comfy.org/llms.txt

Use this file to discover all available pages before exploring further.

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The ModelMergeWAN2_1 node merges two models by blending their components using weighted averages. It supports different model sizes including 1.3B models with 30 blocks and 14B models with 40 blocks, with special handling for image to video models that include an extra image embedding component. Each component of the models can be individually weighted to control the blending ratio between the two input models.

​
Inputs

ParameterData TypeRequiredRangeDescription
model1MODELYes-First model to merge
model2MODELYes-Second model to merge
patch_embedding.FLOATYes0.0 - 1.0Weight for patch embedding component (default: 1.0)
time_embedding.FLOATYes0.0 - 1.0Weight for time embedding component (default: 1.0)
time_projection.FLOATYes0.0 - 1.0Weight for time projection component (default: 1.0)
text_embedding.FLOATYes0.0 - 1.0Weight for text embedding component (default: 1.0)
img_emb.FLOATYes0.0 - 1.0Weight for image embedding component, used in image to video models (default: 1.0)
blocks.0.FLOATYes0.0 - 1.0Weight for block 0 (default: 1.0)
blocks.1.FLOATYes0.0 - 1.0Weight for block 1 (default: 1.0)
blocks.2.FLOATYes0.0 - 1.0Weight for block 2 (default: 1.0)
blocks.3.FLOATYes0.0 - 1.0Weight for block 3 (default: 1.0)
blocks.4.FLOATYes0.0 - 1.0Weight for block 4 (default: 1.0)
blocks.5.FLOATYes0.0 - 1.0Weight for block 5 (default: 1.0)
blocks.6.FLOATYes0.0 - 1.0Weight for block 6 (default: 1.0)
blocks.7.FLOATYes0.0 - 1.0Weight for block 7 (default: 1.0)
blocks.8.FLOATYes0.0 - 1.0Weight for block 8 (default: 1.0)
blocks.9.FLOATYes0.0 - 1.0Weight for block 9 (default: 1.0)
blocks.10.FLOATYes0.0 - 1.0Weight for block 10 (default: 1.0)
blocks.11.FLOATYes0.0 - 1.0Weight for block 11 (default: 1.0)
blocks.12.FLOATYes0.0 - 1.0Weight for block 12 (default: 1.0)
blocks.13.FLOATYes0.0 - 1.0Weight for block 13 (default: 1.0)
blocks.14.FLOATYes0.0 - 1.0Weight for block 14 (default: 1.0)
blocks.15.FLOATYes0.0 - 1.0Weight for block 15 (default: 1.0)
blocks.16.FLOATYes0.0 - 1.0Weight for block 16 (default: 1.0)
blocks.17.FLOATYes0.0 - 1.0Weight for block 17 (default: 1.0)
blocks.18.FLOATYes0.0 - 1.0Weight for block 18 (default: 1.0)
blocks.19.FLOATYes0.0 - 1.0Weight for block 19 (default: 1.0)
blocks.20.FLOATYes0.0 - 1.0Weight for block 20 (default: 1.0)
blocks.21.FLOATYes0.0 - 1.0Weight for block 21 (default: 1.0)
blocks.22.FLOATYes0.0 - 1.0Weight for block 22 (default: 1.0)
blocks.23.FLOATYes0.0 - 1.0Weight for block 23 (default: 1.0)
blocks.24.FLOATYes0.0 - 1.0Weight for block 24 (default: 1.0)
blocks.25.FLOATYes0.0 - 1.0Weight for block 25 (default: 1.0)
blocks.26.FLOATYes0.0 - 1.0Weight for block 26 (default: 1.0)
blocks.27.FLOATYes0.0 - 1.0Weight for block 27 (default: 1.0)
blocks.28.FLOATYes0.0 - 1.0Weight for block 28 (default: 1.0)
blocks.29.FLOATYes0.0 - 1.0Weight for block 29 (default: 1.0)
blocks.30.FLOATYes0.0 - 1.0Weight for block 30 (default: 1.0)
blocks.31.FLOATYes0.0 - 1.0Weight for block 31 (default: 1.0)
blocks.32.FLOATYes0.0 - 1.0Weight for block 32 (default: 1.0)
blocks.33.FLOATYes0.0 - 1.0Weight for block 33 (default: 1.0)
blocks.34.FLOATYes0.0 - 1.0Weight for block 34 (default: 1.0)
blocks.35.FLOATYes0.0 - 1.0Weight for block 35 (default: 1.0)
blocks.36.FLOATYes0.0 - 1.0Weight for block 36 (default: 1.0)
blocks.37.FLOATYes0.0 - 1.0Weight for block 37 (default: 1.0)
blocks.38.FLOATYes0.0 - 1.0Weight for block 38 (default: 1.0)
blocks.39.FLOATYes0.0 - 1.0Weight for block 39 (default: 1.0)
head.FLOATYes0.0 - 1.0Weight for head component (default: 1.0)
Note: All weight parameters use a range from 0.0 to 1.0 with 0.01 step increments. The node supports up to 40 blocks to accommodate different model sizes, where 1.3B models use 30 blocks and 14B models use 40 blocks. The img_emb. parameter is specifically for image to video models.

​
Outputs

Output NameData TypeDescription
modelMODELThe merged model combining components from both input models according to the specified weights