ComfyUI > Nodes > ComfyUI-WithAnyone

ComfyUI Extension: ComfyUI-WithAnyone

Repo Name

ComfyUI-WithAnyone

Author
okdalto (Account age: 3465 days)
Nodes
View all nodes(6)
Latest Updated
2025-12-18
Github Stars
0.02K

How to Install ComfyUI-WithAnyone

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

ComfyUI-WithAnyone Description

ComfyUI-WithAnyone is a ComfyUI port of the WithAnyone model, designed for controllable and ID-consistent image generation, as introduced in the 2025 paper.

ComfyUI-WithAnyone Introduction

ComfyUI-WithAnyone is an extension designed to integrate the WithAnyone model into the ComfyUI environment. This extension allows AI artists to generate images with controllable and identity-consistent features, addressing common issues in face generation such as "copy-paste" artifacts. By using this extension, you can create images where multiple identities are harmoniously integrated, offering a high degree of control over expressions, hairstyles, accessories, and poses. This makes it an invaluable tool for artists looking to create complex compositions with multiple characters while maintaining a consistent style and identity.

How ComfyUI-WithAnyone Works

At its core, ComfyUI-WithAnyone leverages the WithAnyone model, which is designed to generate images that maintain identity consistency while allowing for creative control. The model uses advanced techniques to avoid simply copying and pasting reference faces onto generated images, which can lead to unnatural results. Instead, it balances the similarity to reference images with the flexibility to alter expressions and other features. This is achieved through a combination of text encoders, diffusion models, and a unique approach to embedding identity information, allowing for nuanced control over the generated images.

ComfyUI-WithAnyone Features

  • Identity Consistency: Ensures that the generated faces maintain a strong resemblance to the reference images, preserving key identity features.
  • Controllable Generation: Offers the ability to adjust various aspects of the generated images, such as expressions and accessories, providing artists with creative freedom.
  • Multi-ID Generation: Supports the generation of images with multiple identities, making it ideal for creating group photos or scenes with several characters.
  • Integration with ComfyUI: Seamlessly integrates into the ComfyUI environment, allowing for a node-based workflow that is intuitive and easy to use.

ComfyUI-WithAnyone Models

The extension supports several models, each tailored for specific use cases:

  • WithAnyone 1.0 - FLUX.1: The primary model for general use, offering a balance between identity consistency and creative control.
  • WithAnyone.K.preview - FLUX.1 Kontext: Designed for text-to-image generation, this model is suitable for scenarios where multiple identities need to be generated from textual descriptions.
  • WithAnyone.Ke.preview - FLUX.1 Kontext: Focused on face editing, this model allows for detailed modifications to existing images, leveraging the editing capabilities of the FLUX.1 Kontext.

What's New with ComfyUI-WithAnyone

Recent updates have introduced several enhancements to the extension:

  • ICLR 2026 Acceptance: The WithAnyone model has been recognized at the ICLR 2026 conference, highlighting its innovative approach to image generation.
  • Training Codebase Release: The training codebase is now available, allowing for further customization and experimentation.
  • Hugging Face Space Demo: A new demo is available on Hugging Face, providing an interactive way to explore the capabilities of the model.

Troubleshooting ComfyUI-WithAnyone

If you encounter issues while using the extension, here are some common problems and solutions:

  • Model Loading Error: If you see an error like assert 'detection' in self.models, manually move the downloaded model directory to the correct location as specified in the installation instructions.
  • Face Bounding Boxes: Ensure that face bounding boxes are correctly provided, either automatically or manually, to guide the placement of faces in the generated images.

Learn More about ComfyUI-WithAnyone

To further explore the capabilities of ComfyUI-WithAnyone, consider the following resources:

  • WithAnyone Project Page: Offers detailed information about the WithAnyone model and its development.
  • Hugging Face Demo: An interactive demo to experiment with the model's features.
  • Community Forums: Engage with other AI artists and developers to share experiences and tips for using ComfyUI-WithAnyone effectively. By utilizing these resources, you can enhance your understanding and application of the ComfyUI-WithAnyone extension, unlocking new creative possibilities in your AI art projects.

ComfyUI-WithAnyone Related Nodes

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.

ComfyUI-WithAnyone detailed guide | ComfyUI