Save 4 hours! We auto-setup your workflow! Free!

Drop your workflow.json — we handle every dependency, custom node, and model. Just open the link and run.

Auto-Setup Workflow Json (Free) Now!
ComfyUI > Nodes > ComfyUI-KleinRefGrid > Flux Klein RefGrid

ComfyUI Node: Flux Klein RefGrid

Class Name

FluxKleinRefGrid

Category
conditioning/flux_klein
Author
xb1n0ry (Account age: 2389days)
Extension
ComfyUI-KleinRefGrid
Latest Updated
2026-04-20
Github Stars
0.05K

How to Install ComfyUI-KleinRefGrid

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

Flux Klein RefGrid Description

Facilitates creation of reference grid from images for AI art generation, enhancing model conditioning with VAE latent space.

Flux Klein RefGrid:

The FluxKleinRefGrid node is designed to facilitate the creation of a reference grid from a set of images, which can be used in AI art generation workflows. This node is particularly useful for artists who want to incorporate multiple image references into their creative process, allowing for a more nuanced and complex conditioning of AI models. By compiling up to four images into a single grid, the node encodes this grid into a latent space representation using a Variational Autoencoder (VAE). This latent representation can then be scaled and integrated into the conditioning process of AI models, enhancing the model's ability to generate art that reflects the characteristics of the reference images. The primary goal of the FluxKleinRefGrid is to streamline the integration of multiple visual references, making it easier for artists to experiment with and influence the output of AI-generated art.

Flux Klein RefGrid Input Parameters:

conditioning

The conditioning parameter is a crucial input that represents the initial state or context in which the node operates. It is used to set the baseline conditions for the AI model, which will be modified by the reference grid. This parameter ensures that the model's output is influenced by the reference images, allowing for more controlled and predictable results.

vae

The vae parameter refers to the Variational Autoencoder used to encode the image grid into a latent space. This encoding process is essential for transforming the visual information from the images into a format that the AI model can process and understand. The VAE helps in capturing the essential features of the images, which are then used to condition the model's output.

strength

The strength parameter is a floating-point value that determines the intensity of the influence that the reference grid has on the conditioning process. It ranges from -10.0 to 10.0, with a default value of 1.0. A higher strength value increases the impact of the reference images on the model's output, while a lower value reduces it. This parameter allows artists to fine-tune the balance between the reference images and the model's inherent characteristics.

image_list

The image_list parameter is a string that contains a JSON-encoded list of image paths. This list specifies the images to be included in the reference grid. The node requires at least one image to function, and it can process up to four images. The images are loaded, resized, and compiled into a grid, which is then encoded into the latent space. This parameter is essential for defining the visual references that will influence the AI model's output.

Flux Klein RefGrid Output Parameters:

conditioning

The conditioning output is the modified version of the input conditioning, now influenced by the reference grid. This output is crucial for subsequent nodes in the workflow, as it carries the latent representation of the reference images, allowing the AI model to generate art that reflects the characteristics of these images.

grid_image

The grid_image output is the visual representation of the compiled reference grid. It provides a tangible view of the images that have been integrated into the conditioning process. This output can be used for previewing the reference grid or for further processing in the AI art generation workflow.

Flux Klein RefGrid Usage Tips:

  • Ensure that the image_list contains valid paths to images, as the node requires at least one image to function properly. Use up to four images for optimal results.
  • Adjust the strength parameter to control the influence of the reference images on the model's output. Experiment with different values to achieve the desired balance between the reference images and the model's inherent characteristics.

Flux Klein RefGrid Common Errors and Solutions:

  • Explanation: This error occurs when the image_list is empty or does not contain valid image paths.
  • Solution: Ensure that the image_list parameter contains at least one valid image path. Check the format and content of the JSON-encoded string to confirm that it specifies the correct paths to the images you want to use.

Flux Klein RefGrid Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI-KleinRefGrid
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.