ComfyUI Node: Pre CFG multiplier

Pre CFG multiplier:

The Pre CFG multiplier node is designed to adjust the influence of conditioning and unconditioning signals in your AI model. This node allows you to scale the strength of these signals, either individually or together, by a specified value. By doing so, it provides you with greater control over the model's behavior, enabling you to fine-tune the output to better match your artistic vision. This node is particularly useful for balancing the effects of different conditioning inputs, ensuring that neither overpowers the other unless desired. The main goal of the Pre CFG multiplier is to offer a flexible and intuitive way to manipulate the conditioning signals, enhancing the creative possibilities for AI artists.

Pre CFG multiplier Input Parameters:

model

This parameter represents the AI model you are working with. It is a required input and serves as the foundation upon which the Pre CFG multiplier will apply its adjustments.

selection

This parameter allows you to choose which signals to scale. The options are both, cond, and uncond. Selecting both will scale both conditioning and unconditioning signals, cond will scale only the conditioning signal, and uncond will scale only the unconditioning signal. This flexibility lets you target specific parts of the model's behavior for adjustment.

value

This parameter specifies the scaling factor to be applied to the selected signals. It is a floating-point number with a default value of 0, a minimum value of -100.0, and a maximum value of 100.0. The step size for adjustments is 0.01, allowing for precise control. The value determines how much the selected signals will be multiplied, with positive values increasing their influence and negative values decreasing it.

enabled

This boolean parameter determines whether the Pre CFG multiplier is active. When set to True, the node will apply the specified scaling to the selected signals. If set to False, the node will not make any changes to the model. The default value is True.

Pre CFG multiplier Output Parameters:

model

The output is the modified AI model with the applied scaling adjustments. This model will have its conditioning and/or unconditioning signals scaled according to the specified parameters, allowing for more refined control over its behavior.

Pre CFG multiplier Usage Tips:

• Use the selection parameter to target specific signals for scaling, allowing you to fine-tune the balance between conditioning and unconditioning inputs.
• Experiment with different value settings to see how they affect the model's output. Small adjustments can lead to significant changes in the generated results.
• Toggle the enabled parameter to quickly compare the effects of the scaling adjustments with the original model behavior.

Pre CFG multiplier Common Errors and Solutions:

ValueError: Invalid selection option

• Explanation: This error occurs if an invalid option is provided for the selection parameter.
• Solution: Ensure that the selection parameter is set to one of the following options: both, cond, or uncond.

TypeError: Model input is not valid

• Explanation: This error indicates that the provided model input is not compatible with the Pre CFG multiplier node.
• Solution: Verify that the model input is correctly specified and is of the type MODEL.

ValueError: Scaling value out of range

• Explanation: This error occurs if the value parameter is set outside the allowed range of -100.0 to 100.0.
• Solution: Adjust the value parameter to be within the specified range.