Skip to main content
The PerturbedAttentionGuidance node applies perturbed attention guidance to a diffusion model to enhance generation quality. It modifies the modelโ€™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

ParameterDescriptionData TypeRequiredRange
modelThe diffusion model to apply perturbed attention guidance toMODELYes-
scaleThe 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.FLOATNo0.0 - 100.0

Outputs

Output NameDescriptionData Type
modelThe modified model with perturbed attention guidance appliedMODEL
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