PerturbedAttentionGuidance - ComfyUI Built-in Node Documentation

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

The PerturbedAttentionGuidance node applies perturbed attention guidance to a diffusion model to enhance generation quality. It modifies the model’s self-attention mechanism during sampling by replacing it with a simplified version that focuses on value projections. This technique helps improve the coherence and quality of generated images by adjusting the conditional denoising process.

Inputs

Parameter	Description	Data Type	Required	Range
model	The diffusion model to apply perturbed attention guidance to	MODEL	Yes	-
scale	The strength of the perturbed attention guidance effect (default: 3.0). When set to 0, the node has no effect and returns the original denoised result.	FLOAT	No	0.0 - 100.0

Outputs

Output Name	Description	Data Type
model	The modified model with perturbed attention guidance applied	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): b4bcb5e8a0bf990d36d2865c58e6fbf3c9cee9d446f5aced987ddd04387d2b4c