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-Omnichar > Character Reference

ComfyUI Node: Character Reference

Class Name

OmnicharCharacterReference

Category
Omnichar
Author
omnichar (Account age: 118days)
Extension
ComfyUI-Omnichar
Latest Updated
2026-10-11
Github Stars
0.08K

How to Install ComfyUI-Omnichar

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

Character Reference Description

Manages character references in ComfyUI-Omnichar framework for efficient AI art creation.

Character Reference:

The OmnicharCharacterReference node is designed to manage and utilize character references within the ComfyUI-Omnichar framework. This node plays a crucial role in handling character data by allowing you to work with character references efficiently. It is particularly useful for AI artists who need to integrate character references into their workflows, ensuring that each reference is correctly processed and utilized in the creation of AI-generated art. The node's primary function is to facilitate the seamless integration of character references into various models, enhancing the creative process by providing a structured approach to managing these references. By leveraging this node, you can ensure that character references are accurately represented and utilized, leading to more coherent and contextually relevant outputs in your AI art projects.

Character Reference Input Parameters:

conditioning

This parameter represents the conditioning input required by the node. It is used to attach character references as latents, which are essential for models that perform edits based on these references. The conditioning input ensures that the references are correctly aligned with the model's requirements, allowing for precise and contextually accurate modifications. There are no specific minimum, maximum, or default values provided for this parameter, as it is dependent on the model's conditioning requirements.

refs

The refs parameter is a collection of character references that the node processes. These references are crucial for the node's operation, as they provide the necessary data for generating the desired outputs. The parameter impacts the node's execution by determining the number of references that will be attached as latents. The node expects a list of references, and the number of references should match the character's reference count to ensure accurate processing. There are no explicit minimum, maximum, or default values for this parameter, as it is contingent on the character's reference data.

vae

This parameter refers to the Variational Autoencoder (VAE) used to encode each reference. The VAE is an essential component that transforms the references into a latent space, enabling the model to utilize them effectively. The vae parameter ensures that the references are encoded correctly, which is vital for maintaining the integrity and accuracy of the character data. The node recommends using the model's own VAE to ensure compatibility and optimal performance. There are no specific minimum, maximum, or default values for this parameter, as it depends on the VAE configuration used by the model.

Character Reference Output Parameters:

conditioning

The output conditioning parameter represents the modified conditioning data that includes the attached reference latents. This output is crucial for models that require reference-based conditioning, as it ensures that the references are correctly integrated into the model's processing pipeline. The conditioning output allows the model to make informed decisions based on the provided references, leading to more accurate and contextually relevant outputs. The importance of this output lies in its ability to enhance the model's understanding and utilization of character references, ultimately improving the quality of the generated art.

Character Reference Usage Tips:

  • Ensure that the number of references provided matches the character's reference count to avoid processing errors and ensure accurate results.
  • Use the model's own VAE for encoding references to maintain compatibility and achieve optimal performance.
  • Feed the conditioning output to both positive and negative conditioning inputs of the model to ensure comprehensive utilization of the reference data.

Character Reference Common Errors and Solutions:

Decode Character sent no references. Check its reference set and maximum.

  • Explanation: This error occurs when the node does not receive any references from the Decode Character node, which is essential for its operation.
  • Solution: Verify that the Decode Character node is correctly configured and that it is sending the appropriate reference set. Ensure that the maximum number of references is set correctly to avoid this issue.

Character Reference Related Nodes

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

Character Reference