Skip to main content
The FreeU_V2 node enhances image generation quality by applying frequency-based modifications to a diffusion model’s U-Net architecture. It uses configurable scaling factors to adjust feature channels in different blocks, improving output without requiring additional training.

Inputs

ParameterDescriptionData TypeRequiredRange
modelThe diffusion model to apply FreeU enhancement toMODELYes-
b1Backbone feature scaling factor for the first block (default: 1.3)FLOATYes0.0 - 10.0
b2Backbone feature scaling factor for the second block (default: 1.4)FLOATYes0.0 - 10.0
s1Skip feature scaling factor for the first block (default: 0.9)FLOATYes0.0 - 10.0
s2Skip feature scaling factor for the second block (default: 0.2)FLOATYes0.0 - 10.0

Outputs

Output NameDescriptionData Type
modelThe enhanced diffusion model with FreeU modifications 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): adbbf0934f4c17fa736035b1396d26d6a5c847fd19a981ddd42d9624bd90e619