ComfyUI  >  Nodes  >  Efficiency Nodes for ComfyUI Version 2.0+ >  XY Input: Control Net

ComfyUI Node: XY Input: Control Net

Class Name

XY Input: Control Net

Category
Efficiency Nodes/XY Inputs
Author
jags111 (Account age: 3922 days)
Extension
Efficiency Nodes for ComfyUI Version 2.0...
Latest Updated
8/7/2024
Github Stars
0.8K

How to Install Efficiency Nodes for ComfyUI Version 2.0+

Install this extension via the ComfyUI Manager by searching for  Efficiency Nodes for ComfyUI Version 2.0+
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter Efficiency Nodes for ComfyUI Version 2.0+ in the search bar
After installation, click the  Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • High-speed GPU machines
  • 200+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 50+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

XY Input: Control Net Description

Facilitates parameter manipulation and control within Control Net for AI art generation through grid image creation.

XY Input: Control Net:

The XY Input: Control Net node is designed to facilitate the manipulation and control of various parameters within a Control Net framework, specifically for AI art generation. This node allows you to create a grid of images by varying two parameters along the X and Y axes, providing a visual representation of how different parameter values affect the output. By leveraging this node, you can efficiently explore the impact of parameters such as strength, start percent, and end percent on the generated images, enabling a more intuitive and comprehensive understanding of the Control Net's behavior. This node is particularly beneficial for fine-tuning and optimizing the performance of your AI models, making it an essential tool for AI artists looking to achieve precise and desired results.

XY Input: Control Net Input Parameters:

control_net

This parameter represents the Control Net model that will be used for generating the images. It is essential for defining the network that will process the input image and apply the specified parameters.

image

The image parameter is the input image that will be processed by the Control Net. This image serves as the base for generating the output images with varying parameters.

target_parameter

This parameter specifies which parameter will be varied along the X or Y axis. Options include "strength", "start_percent", and "end_percent". The choice of target parameter determines the type of variation applied to the Control Net.

batch_count

The batch_count parameter defines the number of images to be generated along each axis. It determines the granularity of the parameter variation, with higher values providing more detailed exploration.

first_strength

This parameter sets the initial strength value for the Control Net when varying the "strength" parameter. It defines the starting point for the strength variation.

last_strength

This parameter sets the final strength value for the Control Net when varying the "strength" parameter. It defines the endpoint for the strength variation.

first_start_percent

This parameter sets the initial start percent value for the Control Net when varying the "start_percent" parameter. It defines the starting point for the start percent variation.

last_start_percent

This parameter sets the final start percent value for the Control Net when varying the "start_percent" parameter. It defines the endpoint for the start percent variation.

first_end_percent

This parameter sets the initial end percent value for the Control Net when varying the "end_percent" parameter. It defines the starting point for the end percent variation.

last_end_percent

This parameter sets the final end percent value for the Control Net when varying the "end_percent" parameter. It defines the endpoint for the end percent variation.

strength

The strength parameter specifies the overall strength of the Control Net's effect on the input image. It is used when varying other parameters to maintain a consistent strength level.

start_percent

The start_percent parameter defines the starting point of the Control Net's effect on the input image. It is used when varying other parameters to maintain a consistent start percent level.

end_percent

The end_percent parameter defines the endpoint of the Control Net's effect on the input image. It is used when varying other parameters to maintain a consistent end percent level.

plot_type

This parameter specifies the types of variations to be applied along the X and Y axes. It is a string in the format "X_type, Y_type", where X_type and Y_type are the parameters to be varied.

X_batch_count

The X_batch_count parameter defines the number of images to be generated along the X axis. It determines the granularity of the parameter variation along the X axis.

X_first_value

This parameter sets the initial value for the parameter varied along the X axis. It defines the starting point for the X axis variation.

X_last_value

This parameter sets the final value for the parameter varied along the X axis. It defines the endpoint for the X axis variation.

Y_batch_count

The Y_batch_count parameter defines the number of images to be generated along the Y axis. It determines the granularity of the parameter variation along the Y axis.

Y_first_value

This parameter sets the initial value for the parameter varied along the Y axis. It defines the starting point for the Y axis variation.

Y_last_value

This parameter sets the final value for the parameter varied along the Y axis. It defines the endpoint for the Y axis variation.

cnet_stack

The cnet_stack parameter allows you to provide additional Control Net configurations that will be applied to each generated image. It is useful for stacking multiple Control Net effects.

XY Input: Control Net Output Parameters:

x_entry

The x_entry output parameter provides the results of the parameter variation along the X axis. It includes the type of parameter varied and the corresponding values for each generated image.

y_entry

The y_entry output parameter provides the results of the parameter variation along the Y axis. It includes the type of parameter varied and the corresponding values for each generated image.

XY Input: Control Net Usage Tips:

  • Experiment with different batch_count values to find the optimal granularity for your parameter variations.
  • Use the cnet_stack parameter to combine multiple Control Net effects and explore their combined impact on the generated images.
  • Start with a smaller range for first_strength and last_strength to understand the sensitivity of the Control Net to strength variations before expanding the range.

XY Input: Control Net Common Errors and Solutions:

"Batch count cannot be zero"

  • Explanation: The batch_count parameter is set to zero, which means no images will be generated.
  • Solution: Ensure that the batch_count parameter is set to a value greater than zero.

"Invalid plot_type format"

  • Explanation: The plot_type parameter is not in the correct format "X_type, Y_type".
  • Solution: Ensure that the plot_type parameter is a string in the format "X_type, Y_type", where X_type and Y_type are valid parameter types.

"Control Net model not provided"

  • Explanation: The control_net parameter is missing or not specified.
  • Solution: Ensure that the control_net parameter is provided and points to a valid Control Net model.

"Image input not provided"

  • Explanation: The image parameter is missing or not specified.
  • Solution: Ensure that the image parameter is provided and points to a valid input image.

XY Input: Control Net Related Nodes

Go back to the extension to check out more related nodes.
Efficiency Nodes for ComfyUI Version 2.0+
RunComfy

© Copyright 2024 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals.