ComfyUI Node: Manual scheduler

Class Name

Manual scheduler

Category
sampling/custom_sampling/schedulers
Author
Extraltodeus (Account age: 3204days)
Extension
sigmas_tools_and_the_golden_scheduler
Latest Updated
2024-06-22
Github Stars
0.05K

How to Install sigmas_tools_and_the_golden_scheduler

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

Manual scheduler Description

Versatile node for precise sigma value control in AI art sampling, enabling customized noise schedules for higher-quality outputs.

Manual scheduler:

The Manual scheduler is a versatile node designed to provide you with precise control over the scheduling of sigma values during the sampling process. This node is particularly useful for AI artists who want to fine-tune the noise levels at each step of their model's sampling process, allowing for more customized and potentially higher-quality outputs. By manually specifying the sigma values, you can experiment with different noise schedules to achieve the desired artistic effect, making this node an essential tool for those looking to push the boundaries of their creative projects.

Manual scheduler Input Parameters:

model

This parameter specifies the model to be used for sampling. It is a required input and ensures that the scheduler has the necessary model context to generate sigma values.

steps

This integer parameter determines the number of steps in the sampling process. The default value is 10, with a minimum of 1 and a maximum of 10000. Adjusting this parameter affects the granularity of the sampling process, with more steps providing finer control over the noise levels.

model_type

This parameter allows you to select the type of model you are using, with options including "SD1", "SDXL", and "SVD". This selection helps the scheduler to align its sigma values with the specific characteristics of the chosen model type.

force_sigma_min

This boolean parameter, which defaults to False, determines whether the minimum sigma value should be forced. When set to True, the scheduler ensures that the minimum sigma value is included in the generated sigma values, which can be useful for certain types of sampling processes.

Manual scheduler Output Parameters:

SIGMAS

The output of the Manual scheduler is a tensor of sigma values. These values represent the noise levels at each step of the sampling process, allowing you to control the denoising process precisely. The sigma values are crucial for achieving the desired artistic effect, as they influence the level of detail and smoothness in the generated images.

Manual scheduler Usage Tips:

  • Experiment with different steps values to find the optimal balance between detail and smoothness in your images.
  • Use the model_type parameter to ensure that the sigma values are aligned with the specific characteristics of your model, which can improve the quality of the output.
  • If you need to include the minimum sigma value in your sampling process, set the force_sigma_min parameter to True to ensure it is part of the generated sigma values.

Manual scheduler Common Errors and Solutions:

"Model not specified"

  • Explanation: This error occurs when the model parameter is not provided.
  • Solution: Ensure that you specify a valid model in the model parameter before running the scheduler.

"Invalid number of steps"

  • Explanation: This error occurs when the steps parameter is set to a value outside the allowed range (1 to 10000).
  • Solution: Adjust the steps parameter to a value within the allowed range.

"Unsupported model type"

  • Explanation: This error occurs when an invalid option is selected for the model_type parameter.
  • Solution: Choose a valid model type from the available options: "SD1", "SDXL", or "SVD".

"Force sigma min must be a boolean"

  • Explanation: This error occurs when the force_sigma_min parameter is not set to a boolean value.
  • Solution: Ensure that the force_sigma_min parameter is set to either True or False.

Manual scheduler Related Nodes

Go back to the extension to check out more related nodes.
sigmas_tools_and_the_golden_scheduler
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.