Visit ComfyUI Online for ready-to-use ComfyUI environment
Enhances conditioning process by scaling delta to match conditioning, maintaining balance and proportion seamlessly.
The ConditioningAddConDeltaAutoScale
node is designed to enhance your conditioning process by applying a conditioning delta to an existing conditioning. This node automatically scales the delta to match the conditioning by calculating the ratio of the means of the two vectors involved. This ensures that the delta is appropriately adjusted to the scale of the conditioning, providing a seamless integration of the delta's effects. The primary benefit of this node is its ability to maintain the balance and proportion of the conditioning while incorporating the delta, which can be particularly useful in scenarios where precise adjustments are needed without manually calculating scaling factors. This node is essential for artists looking to fine-tune their conditioning with added deltas, ensuring that the modifications are both effective and harmonious with the original conditioning.
This parameter represents the base conditioning to which the delta will be applied. It is crucial as it serves as the foundation for the modifications introduced by the delta. The conditioning is expected to be in a specific format that the node can process.
The condelta
parameter specifies the conditioning delta to be applied. It is essentially a set of modifications or adjustments that you want to integrate into the base conditioning. The delta is selected from a list of available options, and its name is typically associated with a specific LoRA (Low-Rank Adaptation) model.
This parameter determines the method used to calculate the scaling ratio between the conditioning and the delta. You can choose from "mean," "max," or "median," with "median" being the default option. The choice of ratio type affects how the delta is scaled to match the conditioning, influencing the final output's balance and proportion.
The strength
parameter controls the intensity of the delta's application to the conditioning. It is a float value with a default of 1.0, allowing for fine-tuning with a step of 0.01. The range is from -100.0 to 100.0, providing flexibility in either amplifying or diminishing the delta's effect.
This boolean parameter, when set to true, ensures that the values of the ConDelta are clamped, preventing them from exceeding a specified range. This can be useful for maintaining stability and preventing extreme values that could disrupt the conditioning.
The clamp_value
parameter sets the maximum absolute value for clamping the ConDelta. It is a float with a default of 3.0 and a step of 0.01. This parameter works in conjunction with the clamp
parameter to ensure that the delta values remain within a controlled range.
The output of this node is the modified conditioning, which incorporates the scaled delta. This output retains the original conditioning's structure while integrating the adjustments specified by the delta. The result is a refined conditioning that reflects the desired modifications, providing a balanced and proportionate enhancement to the original input.
ratio_type
settings to see how they affect the scaling of the delta. This can help you achieve the desired balance between the conditioning and the delta.strength
parameter to control the intensity of the delta's effect. A higher strength can amplify the delta's impact, while a lower strength can provide subtle adjustments.condelta
could not be located in the available list.condelta
name is correct and that it exists in the list of available options.clamp_value
is set outside the permissible range.clamp_value
to fall within the acceptable range, ensuring it is a positive float value.RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Playground, enabling artists to harness the latest AI tools to create incredible art.