CLIPMergeSimple - ComfyUI Built-in Node Documentation

CLIPMergeSimple is a model merging node that combines two CLIP text encoder models based on a specified ratio.

CLIPMergeSimple is a model merging node that combines two CLIP text encoder models based on a specified ratio. It clones the first CLIP model and applies weighted patches from the second CLIP model, skipping position IDs and logit scale components, to produce a hybrid model that blends features from both sources.

Inputs

Parameter	Description	Data Type	Required	Range
clip1	The first CLIP model to be merged. It serves as the base model for the merging process.	CLIP	Yes	-
clip2	The second CLIP model to be merged. Its key patches, except for position IDs and logit scale, are applied to the first model based on the specified ratio.	CLIP	Yes	-
ratio	Determines the proportion of features from the second model to blend into the first model. A ratio of 1.0 means fully adopting the second model’s features, while 0.0 retains only the first model’s features. Default: 1.0.	FLOAT	Yes	0.0 - 1.0 (step: 0.01)

Outputs

Output Name	Description	Data Type
clip	The resulting merged CLIP model, incorporating features from both input models according to the specified ratio.	CLIP

Merging Mechanism Explained

Merging Algorithm

The node uses weighted averaging to merge the two models:

1. Clone Base Model: First clones clip1 as the base model
2. Get Patches: Obtains all key patches from clip2
3. Filter Special Keys: Skips keys ending with .position_ids and .logit_scale
4. Apply Weighted Merge: Uses the formula (1.0 - ratio) * clip1 + ratio * clip2

Ratio Parameter Explained

• ratio = 0.0: Fully uses clip1, ignores clip2
• ratio = 0.5: 50% contribution from each model
• ratio = 1.0: Fully uses clip2, ignores clip1

Use Cases

1. Model Style Fusion: Combine characteristics of CLIP models trained on different data
2. Performance Optimization: Balance strengths and weaknesses of different models
3. Experimental Research: Explore combinations of different CLIP encoders

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): 42c4b2042c56c3f21a9416aa577e2d41fef1dcc749c4e5c7953851110a4fb6bc