ComfyUI  >  Nodes  >  ComfyUI Impact Pack >  CfgScheduleHookProvider

ComfyUI Node: CfgScheduleHookProvider

Class Name


Dr.Lt.Data (Account age: 458 days)
ComfyUI Impact Pack
Latest Updated
Github Stars

How to Install ComfyUI Impact Pack

Install this extension via the ComfyUI Manager by searching for  ComfyUI Impact Pack
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI Impact Pack 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

CfgScheduleHookProvider Description

Dynamically adjust CFG settings for iterative image upscaling with scheduling mechanism for AI artists.


The CfgScheduleHookProvider node is designed to dynamically adjust the configuration (CFG) settings during the iterative process of image upscaling. This node is particularly useful for AI artists who want to fine-tune the CFG values progressively, ensuring that the final output meets their desired quality and detail. By leveraging a scheduling mechanism, this node allows for a smooth transition of CFG values across iterations, enhancing the overall control and precision in the upscaling process. The primary goal of this node is to provide a flexible and automated way to manage CFG settings, making it easier to achieve optimal results without manual intervention at each step.

CfgScheduleHookProvider Input Parameters:


This parameter determines the type of schedule to be used for the iteration process. The available option is simple, which applies a straightforward linear progression of CFG values across iterations. This parameter ensures that the CFG adjustments are applied consistently throughout the upscaling process.


This parameter specifies the target configuration (CFG) value that the node aims to reach by the end of the iteration process. It is a floating-point number with a default value of 3.0, a minimum value of 0.0, and a maximum value of 100.0. Adjusting this parameter allows you to control the intensity and quality of the upscaling, with higher values generally leading to more detailed and refined outputs.

CfgScheduleHookProvider Output Parameters:


The output of this node is a PK_HOOK, which is a hook object that encapsulates the scheduling logic for CFG adjustments. This hook is used within the upscaling pipeline to apply the specified CFG schedule, ensuring that the target CFG value is progressively approached during the iterations. The hook's function is crucial for maintaining the desired CFG progression and achieving the intended upscaling results.

CfgScheduleHookProvider Usage Tips:

  • To achieve a gradual and smooth transition of CFG values, set the schedule_for_iteration parameter to simple and adjust the target_cfg to your desired final value.
  • Experiment with different target_cfg values to find the optimal setting for your specific upscaling task. Higher values can enhance detail, but may also increase processing time.

CfgScheduleHookProvider Common Errors and Solutions:

[ERROR] Invalid schedule_for_iteration value

  • Explanation: The provided value for schedule_for_iteration is not recognized.
  • Solution: Ensure that the value is set to simple, as it is the only supported option.

[ERROR] target_cfg out of range

  • Explanation: The target_cfg value is outside the allowed range (0.0 to 100.0).
  • Solution: Adjust the target_cfg value to be within the specified range to avoid this error.

CfgScheduleHookProvider Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI Impact Pack

© 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.