ComfyUI>Workflows>CatVTON | Amazing Virtual Try-On

CatVTON | Amazing Virtual Try-On

Workflow Name: RunComfy/CatVTON
Workflow ID: 0000...1152
CatVTON, a state-of-the-art diffusion model, revolutionizes virtual try-on by making it both simpler and more precise. This ComfyUI CatVTON workflow walks you through each step of the process, from preparing your images to generating masks and fine-tuning parameters, ensuring you achieve professional-level virtual try-on results.
The CatVTON model was created by Zheng Chong et al. from Sun Yat-Sen University, Pixocial Technology, Pengcheng Laboratory, and SIAT. Credit goes to their creative work!

ComfyUI CatVTON Workflow

CatVTON for Virtual Try-On in ComfyUI
Want to run this workflow?
  • Fully operational workflows
  • No missing nodes or models
  • No manual setups required
  • Features stunning visuals

ComfyUI CatVTON Examples

catvton-advanced-ai-virtual-try-on-1152
catvton-advanced-ai-virtual-try-on-1152-example_1.webp
catvton-advanced-ai-virtual-try-on-1152-example_2.webp

CatVTON (A Revolutionary Approach to Virtual Try-On Using Diffusion Models) represents a groundbreaking advancement in virtual try-on technology, introducing a simplified yet powerful approach that relies on spatial concatenation of garment and person images. Now available as a ComfyUI workflow, CatVTON makes creating high-quality virtual try-on images more accessible than ever.

1. Understanding CatVTON#

At its core, CatVTON stands out for its elegantly simple architecture. Unlike traditional virtual try-on solutions that depend on complex components like additional image encoders, ReferenceNet, or text encoders, CatVTON streamlines the process by focusing solely on essential diffusion modules. This minimalist approach not only reduces the model's parameter count significantly but also enhances its efficiency and training process.

2. Getting Started with CatVTON in ComfyUI#

Basic Setup#

  1. Image Preparation
    • Upload a clear photo of your target person
    • Provide a reference image of the desired garment
  2. Mask Generation
    • Use the "AutoMasker" node
    • Select the appropriate clothing category:
      • Overall
      • Upper body
      • Lower body
  3. Parameter Configuration
    • Diffusion Steps: Begin with 42 steps
      • Higher values: Better quality but slower processing
      • Lower values: Faster processing but potentially reduced quality
    • CFG Scale: Start with a value of 50
      • Higher values: More accurate garment transfer
      • Lower values: Greater output variety

Optimization Tips#

For the best possible results:

  • Use high-resolution, well-lit images for both person and garment inputs
  • Experiment with different clothing combinations
  • Fine-tune parameters based on your specific needs

Licensing Information#

CatVTON is released under the Creative Commons BY-NC-SA 4.0 license. This means you can:

  • Share and adapt the material
  • Use it for non-commercial purposes
  • Must provide appropriate attribution
  • Share any modifications under the same license terms

For more detailed information and technical specifications, visit the official CatVTON repository.


So, are you looking for an amazing virtual try-on solution? CatVTON is your answer! Dive into the world of CatVTON and start creating amazing virtual try-on experiences today. At RunComfy, we've set up all the models and environments for you to try! Happy creating!

RunComfy
Copyright 2026 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.