ComfyUI > Nodes > content_aware_tiles > KSampler (Rolling)

ComfyUI Node: KSampler (Rolling)

Class Name

RollingKSampler

Category
tiles
Author
samsartor (Account age: 5064days)
Extension
content_aware_tiles
Latest Updated
2026-01-27
Github Stars
0.02K

How to Install content_aware_tiles

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

KSampler (Rolling) Description

Enhances sampling with a rolling mechanism for seamless, tile-like effects and doubled output size.

KSampler (Rolling):

The RollingKSampler is a specialized node designed to enhance the sampling process by introducing a unique rolling mechanism. This node is particularly useful in scenarios where you want to generate samples with a seamless, tile-like effect. By leveraging a rolling technique, it shifts the input data in a way that wraps around the edges, ensuring continuity and smooth transitions. This is especially beneficial for creating textures or patterns that need to be tiled without visible seams. The node's primary goal is to provide a flexible and efficient way to manipulate input data, allowing for creative and visually appealing outputs. Its ability to double the output size further enhances its utility, making it a versatile tool for artists looking to experiment with different sampling techniques.

KSampler (Rolling) Input Parameters:

double_output

The double_output parameter is a boolean option that determines whether the output should be doubled in size. When set to True, the node will concatenate the sampled output both horizontally and vertically, effectively quadrupling the area of the original sample. This can be particularly useful when you need larger samples for further processing or visualization. The default value is True, allowing for immediate use of the expanded output without additional configuration. This parameter provides flexibility in controlling the output size, enabling you to tailor the results to your specific needs.

KSampler (Rolling) Output Parameters:

samples

The samples output parameter represents the final processed data after the rolling and sampling operations have been applied. This output is a tensor that contains the sampled data, potentially expanded if the double_output parameter is enabled. The importance of this output lies in its seamless and continuous nature, making it ideal for applications requiring tiled patterns or textures. The interpretation of this output is straightforward: it is the enhanced version of the input data, ready for use in various artistic or computational tasks.

KSampler (Rolling) Usage Tips:

  • To create seamless tile patterns, ensure that the input data is suitable for wrapping, as this will enhance the continuity of the output.
  • Utilize the double_output parameter to quickly generate larger samples, which can be beneficial for high-resolution projects or when further processing is required.

KSampler (Rolling) Common Errors and Solutions:

AssertionError: Input tensor is not valid

  • Explanation: This error occurs when the input data is not a valid tensor or does not meet the expected dimensions.
  • Solution: Ensure that the input data is a properly formatted tensor and matches the expected shape requirements.

ValueError: Invalid configuration for rolling offsets

  • Explanation: This error might arise if the rolling offsets are not correctly calculated or applied.
  • Solution: Verify that the input dimensions are appropriate for the rolling operation and that the random offset generation is functioning as intended.

KSampler (Rolling) Related Nodes

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

KSampler (Rolling)