> ## 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.

# CLIPAttentionMultiply - ComfyUI Built-in Node Documentation

> Complete documentation for the CLIPAttentionMultiply node in ComfyUI. Learn its inputs, outputs, parameters and usage.

> This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! [Edit on GitHub](https://github.com/Comfy-Org/embedded-docs/blob/main/comfyui_embedded_docs/docs/CLIPAttentionMultiply/en.md)

The CLIPAttentionMultiply node allows you to adjust the attention mechanism in CLIP models by applying multiplication factors to different components of the self-attention layers. It works by modifying the query, key, value, and output projection weights and biases in the CLIP model's attention mechanism. This experimental node creates a modified copy of the input CLIP model with the specified scaling factors applied.

## Inputs

| Parameter | Data Type | Required | Range      | Description                                                                   |
| --------- | --------- | -------- | ---------- | ----------------------------------------------------------------------------- |
| `clip`    | CLIP      | Yes      | -          | The CLIP model to modify                                                      |
| `q`       | FLOAT     | Yes      | 0.0 - 10.0 | Multiplication factor for query projection weights and biases (default: 1.0)  |
| `k`       | FLOAT     | Yes      | 0.0 - 10.0 | Multiplication factor for key projection weights and biases (default: 1.0)    |
| `v`       | FLOAT     | Yes      | 0.0 - 10.0 | Multiplication factor for value projection weights and biases (default: 1.0)  |
| `out`     | FLOAT     | Yes      | 0.0 - 10.0 | Multiplication factor for output projection weights and biases (default: 1.0) |

## Outputs

| Output Name | Data Type | Description                                                                        |
| ----------- | --------- | ---------------------------------------------------------------------------------- |
| `CLIP`      | CLIP      | Returns a modified CLIP model with the specified attention scaling factors applied |

***

**Source fingerprint (SHA-256):** `1f5c437cb4a372dfd69ad3c10e2b8cfc68821e0fe82dcf37df5e6fd64aa0b436`