ComfyUI > Nodes > ComfyUI-CapitanZiT-Scheduler > CapitanZiT Linear Sigma (for Z-Image Turbo)

ComfyUI Node: CapitanZiT Linear Sigma (for Z-Image Turbo)

Class Name

CapitanZiTLinearSigma

Category
sampling/custom_sampling/sigmas
Author
capitan01R (Account age: 10days)
Extension
ComfyUI-CapitanZiT-Scheduler
Latest Updated
2026-01-16
Github Stars
0.07K

How to Install ComfyUI-CapitanZiT-Scheduler

Install this extension via the ComfyUI Manager by searching for ComfyUI-CapitanZiT-Scheduler
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI-CapitanZiT-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
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

CapitanZiT Linear Sigma (for Z-Image Turbo) Description

Generates a linear sigma schedule for controlled image sampling in Z-Image Turbo processes.

CapitanZiT Linear Sigma (for Z-Image Turbo):

The CapitanZiTLinearSigma node is designed to generate a linear sigma schedule, which is a sequence of values that transition linearly from 1.0 to 0.0. This node is particularly useful in the context of the Z-Image Turbo flow-matching process, where such a schedule is required to control the progression of image sampling or processing steps. By providing a smooth and predictable transition of sigma values, this node helps in achieving consistent and controlled results in image generation tasks. The linear sigma schedule is crucial for ensuring that the image processing pipeline operates efficiently and effectively, allowing for precise control over the sampling process.

CapitanZiT Linear Sigma (for Z-Image Turbo) Input Parameters:

steps

The steps parameter determines the number of intervals in the linear sigma schedule, effectively controlling the granularity of the transition from 1.0 to 0.0. A higher number of steps results in a finer granularity, providing more control points in the schedule, while a lower number of steps results in a coarser transition. This parameter is crucial for tailoring the sigma schedule to specific needs, such as achieving smoother transitions or faster processing times. The steps parameter accepts integer values with a minimum of 1 and a maximum of 100, and it defaults to 9. Adjusting this parameter allows you to balance between the precision of the schedule and the computational resources required.

CapitanZiT Linear Sigma (for Z-Image Turbo) Output Parameters:

SIGMAS

The SIGMAS output is a tensor containing the generated linear sigma schedule. This output represents a sequence of sigma values that linearly decrease from 1.0 to 0.0, based on the specified number of steps. The sigma values are used in image processing tasks to control the influence of noise or other factors during the sampling process. By providing a structured and predictable sequence of values, the SIGMAS output enables precise control over the image generation process, ensuring that the desired effects are achieved consistently across different stages of the pipeline.

CapitanZiT Linear Sigma (for Z-Image Turbo) Usage Tips:

  • To achieve smoother transitions in your image processing tasks, consider increasing the steps parameter to provide more control points in the sigma schedule.
  • If you are working with limited computational resources, you can reduce the steps parameter to speed up the processing time, while still maintaining a reasonable level of control over the sigma schedule.

CapitanZiT Linear Sigma (for Z-Image Turbo) Common Errors and Solutions:

"CUDA error: device-side assert triggered"

  • Explanation: This error may occur if the steps parameter is set to a value that is not supported by the device or if there is a mismatch in the expected data types.
  • Solution: Ensure that the steps parameter is within the valid range (1 to 100) and that your device supports the operations being performed. Check for any data type mismatches and correct them.

"RuntimeError: Expected object of scalar type Float but got scalar type Double for argument"

  • Explanation: This error indicates a type mismatch between expected and provided data types, often occurring when the tensor operations expect a specific type.
  • Solution: Ensure that all input values and operations are using the correct data types, particularly focusing on ensuring that tensors are of type Float as expected by the operations.

CapitanZiT Linear Sigma (for Z-Image Turbo) Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI-CapitanZiT-Scheduler
RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.