ComfyUI  >  Nodes  >  ComfyUI-Portrait-Maker

ComfyUI Extension: ComfyUI-Portrait-Maker

Repo Name

ComfyUI-Portrait-Maker

Author
THtianhao (Account age: 3700 days)
Nodes
View all nodes (20)
Latest Updated
5/22/2024
Github Stars
0.2K

How to Install ComfyUI-Portrait-Maker

Install this extension via the ComfyUI Manager by searching for  ComfyUI-Portrait-Maker
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI-Portrait-Maker 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
  • High-speed GPU machines
  • 200+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 50+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

ComfyUI-Portrait-Maker Description

ComfyUI-Portrait-Maker enhances portrait images using nodes like RetainFace, FaceFusion, and SkinRetouching. It merges, masks, and refines facial features, ensuring high-quality, detailed portrait enhancements.

ComfyUI-Portrait-Maker Introduction

ComfyUI-Portrait-Maker is an extension designed to enhance and simplify the process of creating and editing human portraits using AI. It is an adaptation of the EasyPhoto project, breaking down its processes and adding a series of operations specifically tailored for human portraits. This extension is particularly useful for AI artists who want to generate high-quality, realistic portraits with minimal effort. It offers a range of features that allow for detailed customization and enhancement of portraits, solving common issues such as color transfer, makeup application, and image resolution enhancement.

How ComfyUI-Portrait-Maker Works

ComfyUI-Portrait-Maker operates by integrating various AI models and techniques to perform specific tasks on portrait images. The extension uses nodes, each representing a different operation, such as face detection, image fusion, and color transfer. By connecting these nodes in a workflow, users can apply multiple enhancements and transformations to their portraits. For example, you can start with a basic portrait, apply makeup, adjust skin tones, and enhance the image resolution, all within a single workflow. This modular approach makes it easy to customize and experiment with different effects.

ComfyUI-Portrait-Maker Features

RetainFace PM

  • Description: Performs face detection and matting using models from Model Scope.
  • Customization: Adjust the face crop ratio and select specific faces in multi-face images.
  • Example: Use this node to isolate and enhance a specific face in a group photo.

FaceFusion PM

  • Description: Merges faces from two images.
  • Customization: Choose between Ali's model or Roop's model for merging.
  • Example: Combine features from two different faces to create a new, unique portrait.

RatioMerge2Image PM

  • Description: Merges two images based on a specified ratio.
  • Customization: Set the fusion ratio to control the blend between the two images.
  • Example: Blend a portrait with a background image to create a seamless composite.

MaskMerge2Image PM

  • Description: Merges images using a mask.
  • Customization: Apply a custom mask to control which parts of the images are merged.
  • Example: Replace the background of a portrait while keeping the subject intact.

ReplaceBoxImg PM

  • Description: Replaces a specified area of an image with another image.
  • Customization: Define the box area and ensure the replacement image matches the resolution.
  • Example: Swap out a section of a portrait, such as the eyes or mouth, with a different image.

ExpandMaskFaceWidth PM

  • Description: Expands the width of a mask proportionally.
  • Customization: Set the expansion ratio based on the mask's width.
  • Example: Widen the mask area around a face to include more background.

BoxCropImage PM

  • Description: Crops an image using a defined box.
  • Example: Focus on a specific part of a portrait, such as the face or upper body.

ColorTransfer PM

  • Description: Transfers colors between images.
  • Example: Match the color tones of a portrait to a reference image for a consistent look.

FaceSkin PM

  • Description: Extracts the mask of the facial region from an image.
  • Example: Isolate the face for targeted enhancements like skin smoothing.

MaskDilateErode PM

  • Description: Applies dilation and erosion to masks.
  • Example: Refine the edges of a mask to improve blending with the background.

Skin Retouching PM

  • Description: Applies skin retouching using a specialized model.
  • Example: Smooth out skin imperfections and enhance facial features.

Portrait Enhancement PM

  • Description: Enhances portrait images using models like GPEN and Real-ESRGAN.
  • Example: Improve the overall quality and resolution of a portrait.

ImageResizeTarget PM

  • Description: Resizes images to a target width and height.
  • Example: Standardize the size of portraits for consistent output.

ImageScaleShort PM

  • Description: Scales the smaller dimension of an image proportionally.
  • Example: Resize a portrait while maintaining its aspect ratio.

GetImageInfo PM

  • Description: Extracts the width and height of an image.
  • Example: Use this information to make informed adjustments to image size and composition.

Face Shape Match PM

  • Description: Reduces differences around the face by blending the diffused image with the original.
  • Example: Ensure a natural look when combining different facial features.

Makeup Transfer PM

  • Description: Applies makeup to a portrait using a GAN network model.
  • Example: Experiment with different makeup styles on a portrait.

SuperMakeUpTransfer PM

  • Description: Integrates multiple nodes to apply makeup by merging two images.
  • Example: Create a glamorous look by combining elements from different makeup styles.

SuperColorTransfer PM

  • Description: Integrates multiple nodes to transfer colors between images.
  • Example: Achieve a cohesive color scheme across multiple portraits.

ComfyUI-Portrait-Maker Models

ComfyUI-Portrait-Maker utilizes various models to perform its tasks. Here are some of the key models:

  • RetinaFace: Used for face detection and matting.
  • Ali's Face Fusion Model: Used for merging faces.
  • Roop's Face Fusion Model: Another option for face merging.
  • GPEN: Used for portrait enhancement.
  • Real-ESRGAN: Used for super-resolution enhancement. Each model is designed for specific tasks, and you can choose the appropriate model based on your needs. For example, use GPEN for general portrait enhancement and Real-ESRGAN for improving image resolution.

What's New with ComfyUI-Portrait-Maker

V1.2.0 Update

  • New Features:
  • Added PM_SuperColorTransfer node to simplify the color transfer process.
  • Added PM_SuperMakeUpTransfer node to simplify the makeup transfer process.
  • Introduced v1.2.0 workflow for streamlined operations.

V1.1.0 Update

  • Enhancements:
  • Added blur option to FaceSkin.
  • Introduced PM_FaceShapeMatch node for face shape matching.
  • Added PM_MakeUpTransfer node for makeup transfer.
  • Included a super-resolution model in the PM_PortraitEnhancement node.
  • Updated v1.1.0 workflow.
  • RetinaFace now supports face selection.

V1.0.0 Update

  • Improvements:
  • Added logging for model downloads.
  • Renamed nodes to resolve conflicts with other plugins.
  • Added "roop" model to the FaceFusion PM node.
  • Updated the workflow for better performance.
  • Improved model loading speed.

Troubleshooting ComfyUI-Portrait-Maker

Common Issues and Solutions

  1. Model Download Issues:
  • Problem: The model download is interrupted.
  • Solution: Manually delete the partially downloaded files and restart the download process.
  1. Face Detection Problems:
  • Problem: The face is not detected correctly.
  • Solution: Ensure the input image is clear and well-lit. Adjust the face crop ratio if necessary.
  1. Image Quality Issues:
  • Problem: The output image quality is poor.
  • Solution: Use the Portrait Enhancement PM node with the GPEN or Real-ESRGAN model for better results.
  1. Workflow Errors:
  • Problem: Errors occur when running the workflow.
  • Solution: Check the connections between nodes and ensure all required inputs are provided.

Frequently Asked Questions (FAQs)

  • Q: Can I use my own models with ComfyUI-Portrait-Maker?
  • A: Yes, you can integrate your own models by adding them to the appropriate nodes.
  • Q: How do I update ComfyUI-Portrait-Maker?
  • A: Follow the update instructions provided in the repository to ensure you have the latest features and fixes.
  • Q: What is the best way to enhance image resolution?
  • A: Use the Portrait Enhancement PM node with the Real-ESRGAN model for optimal results.

Learn More about ComfyUI-Portrait-Maker

To further explore the capabilities of ComfyUI-Portrait-Maker, you can refer to the following resources:

  • Tutorials: Detailed guides on how to use each feature and node.
  • Documentation: Comprehensive documentation covering all aspects of the extension.
  • Community Forums: Join the community to ask questions, share your work, and get support from other AI artists. By leveraging these resources, you can maximize the potential of ComfyUI-Portrait-Maker and create stunning AI-generated portraits with ease.

ComfyUI-Portrait-Maker Related Nodes

RunComfy

© Copyright 2024 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals.