ComfyUI Node: 🕹️ CR Multi-ControlNet Stack

🕹️ CR Multi-ControlNet Stack:

The CR Multi-ControlNet Stack node is designed to facilitate the application of multiple ControlNet models in a stacked manner, each with its own switch for activation. This node allows you to combine the effects of several ControlNet models, providing a more nuanced and complex conditioning for your AI-generated images. By enabling or disabling individual ControlNet models within the stack, you can fine-tune the influence of each model on the final output, offering greater control and flexibility in your creative process. This node is particularly useful for AI artists looking to leverage multiple ControlNet models to achieve specific artistic effects or to experiment with different combinations of models to discover new possibilities.

🕹️ CR Multi-ControlNet Stack Input Parameters:

switch_1

This parameter controls whether the first ControlNet model in the stack is active or not. When set to "On", the first ControlNet model will be applied; when set to "Off", it will be ignored. This allows you to selectively enable or disable the first ControlNet model without removing it from the stack. Options: "On", "Off".

controlnet_1

This parameter specifies the first ControlNet model to be used in the stack. You can choose from a list of available ControlNet models. The selected model will be applied to the input image if switch_1 is set to "On". This parameter is crucial for defining the first layer of conditioning. Options: List of available ControlNet models.

controlnet_strength_1

This parameter determines the strength of the first ControlNet model's influence on the final output. A higher value means a stronger influence, while a lower value means a weaker influence. This allows you to adjust the intensity of the first ControlNet model's effect. Range: 0.0 to 1.0.

start_percent_1

This parameter defines the starting point of the first ControlNet model's influence as a percentage of the total processing time. It allows you to control when the first ControlNet model begins to affect the image. Range: 0 to 100.

end_percent_1

This parameter defines the ending point of the first ControlNet model's influence as a percentage of the total processing time. It allows you to control when the first ControlNet model stops affecting the image. Range: 0 to 100.

image_1

This parameter allows you to provide an image that will be used by the first ControlNet model for conditioning. The image serves as a reference or guide for the ControlNet model to influence the final output. This parameter is optional but can significantly impact the results if used.

switch_2

This parameter controls whether the second ControlNet model in the stack is active or not. When set to "On", the second ControlNet model will be applied; when set to "Off", it will be ignored. Options: "On", "Off".

controlnet_2

This parameter specifies the second ControlNet model to be used in the stack. You can choose from a list of available ControlNet models. The selected model will be applied to the input image if switch_2 is set to "On". Options: List of available ControlNet models.

controlnet_strength_2

This parameter determines the strength of the second ControlNet model's influence on the final output. A higher value means a stronger influence, while a lower value means a weaker influence. Range: 0.0 to 1.0.

start_percent_2

This parameter defines the starting point of the second ControlNet model's influence as a percentage of the total processing time. Range: 0 to 100.

end_percent_2

This parameter defines the ending point of the second ControlNet model's influence as a percentage of the total processing time. Range: 0 to 100.

image_2

This parameter allows you to provide an image that will be used by the second ControlNet model for conditioning. This parameter is optional but can significantly impact the results if used.

switch_3

This parameter controls whether the third ControlNet model in the stack is active or not. When set to "On", the third ControlNet model will be applied; when set to "Off", it will be ignored. Options: "On", "Off".

controlnet_3

This parameter specifies the third ControlNet model to be used in the stack. You can choose from a list of available ControlNet models. The selected model will be applied to the input image if switch_3 is set to "On". Options: List of available ControlNet models.

controlnet_strength_3

This parameter determines the strength of the third ControlNet model's influence on the final output. A higher value means a stronger influence, while a lower value means a weaker influence. Range: 0.0 to 1.0.

start_percent_3

This parameter defines the starting point of the third ControlNet model's influence as a percentage of the total processing time. Range: 0 to 100.

end_percent_3

This parameter defines the ending point of the third ControlNet model's influence as a percentage of the total processing time. Range: 0 to 100.

image_3

This parameter allows you to provide an image that will be used by the third ControlNet model for conditioning. This parameter is optional but can significantly impact the results if used.

controlnet_stack

This parameter allows you to provide a pre-defined stack of ControlNet models. Each entry in the stack should be a tuple containing the ControlNet model, image, strength, start percent, and end percent. This parameter is optional but can be used to apply a complex stack of ControlNet models in one go.

🕹️ CR Multi-ControlNet Stack Output Parameters:

controlnet_list

This output parameter provides a list of tuples, each containing a ControlNet model, image, strength, start percent, and end percent. This list represents the stack of ControlNet models that have been applied based on the input parameters. It is useful for understanding the configuration of the applied ControlNet models.

show_help

This output parameter provides a URL to the help documentation for the CR Multi-ControlNet Stack node. It is useful for users who need additional information or guidance on how to use the node effectively.

🕹️ CR Multi-ControlNet Stack Usage Tips:

• Experiment with different combinations of ControlNet models to discover unique artistic effects.
• Use the strength parameters to fine-tune the influence of each ControlNet model for more subtle or pronounced effects.
• Leverage the start and end percent parameters to control the timing of each ControlNet model's influence, allowing for dynamic changes throughout the processing.

🕹️ CR Multi-ControlNet Stack Common Errors and Solutions:

"ControlNet model not found"

• Explanation: This error occurs when the specified ControlNet model cannot be located in the provided path.
• Solution: Ensure that the ControlNet model name is correct and that it exists in the specified directory.

"Image not provided for active ControlNet"

• Explanation: This error occurs when an image is not provided for a ControlNet model that is set to "On".
• Solution: Provide a valid image for each active ControlNet model to ensure proper conditioning.

"Invalid strength value"

• Explanation: This error occurs when the strength value is outside the acceptable range of 0.0 to 1.0.
• Solution: Adjust the strength value to be within the range of 0.0 to 1.0.

"Start percent greater than end percent"

• Explanation: This error occurs when the start percent value is greater than the end percent value.
• Solution: Ensure that the start percent value is less than or equal to the end percent value for each ControlNet model.