ComfyUI  >  Nodes  >  ComfyUI-Florence-2

ComfyUI Extension: ComfyUI-Florence-2

Repo Name


spacepxl (Account age: 303 days)
View all nodes (4)
Latest Updated
Github Stars

How to Install ComfyUI-Florence-2

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

ComfyUI-Florence-2 is a versatile extension supporting large or base models, enabling captioning and bounding box (bbox) task modes, with additional features planned for future updates.

ComfyUI-Florence-2 Introduction

ComfyUI-Florence-2 is an extension designed to enhance your AI art creation experience by integrating the powerful Florence-2 models from Microsoft into the ComfyUI interface. This extension provides initial support for all output types, making it a versatile tool for various artistic needs. Whether you're working on image generation, segmentation, or bounding box tasks, ComfyUI-Florence-2 can help streamline your workflow and improve the quality of your outputs.

How ComfyUI-Florence-2 Works

ComfyUI-Florence-2 works by leveraging the advanced capabilities of the Florence-2 models to process and generate high-quality images based on your input. Think of it as a sophisticated assistant that understands your artistic vision and helps bring it to life. The extension integrates seamlessly with ComfyUI, allowing you to use Florence-2's models for different types of image processing tasks.

For example, if you're working on an image segmentation project, ComfyUI-Florence-2 can help you identify and isolate different parts of an image with precision. Similarly, for tasks involving bounding boxes, the extension can accurately detect and highlight objects within an image. This makes it easier for you to focus on the creative aspects of your work without getting bogged down by technical details.

ComfyUI-Florence-2 Features

ComfyUI-Florence-2 comes with several key features designed to enhance your AI art creation process:

  1. Support for All Output Types: Whether you need image generation, segmentation, or bounding box outputs, ComfyUI-Florence-2 has you covered. This flexibility allows you to tackle a wide range of artistic projects using a single extension.
  2. Customizable Settings: The extension offers various settings that you can adjust to fine-tune the output according to your preferences. For instance, you can modify parameters related to image resolution, segmentation accuracy, and bounding box detection to achieve the desired results.
  3. Seamless Integration with ComfyUI: ComfyUI-Florence-2 integrates smoothly with the ComfyUI interface, making it easy to incorporate into your existing workflow. This ensures that you can start using the extension with minimal setup and disruption.

ComfyUI-Florence-2 Models

The extension includes four different models, each tailored for specific tasks:

  1. Florence-2 Large: This model is ideal for high-resolution image generation and tasks that require detailed outputs. Use this model when you need the highest quality results.
  2. Segmentation Model: Designed for image segmentation tasks, this model helps you identify and isolate different parts of an image with high accuracy. It's perfect for projects that involve separating objects or regions within an image.
  3. Bounding Box Model: This model excels at detecting and highlighting objects within an image using bounding boxes. It's useful for tasks that require object detection and localization.
  4. All-in-One Model: This versatile model supports multiple output types, making it a great choice for projects that involve a combination of image generation, segmentation, and bounding box tasks.

What's New with ComfyUI-Florence-2

The latest updates to ComfyUI-Florence-2 include:

  • Initial Support for All Output Types: The extension now supports image generation, segmentation, and bounding box outputs, providing greater flexibility for your projects.
  • Improved Model Performance: Enhancements to the underlying models ensure better accuracy and quality of the outputs, helping you achieve more refined results. These updates are designed to make ComfyUI-Florence-2 more versatile and powerful, enabling you to tackle a wider range of artistic challenges with ease.

Troubleshooting ComfyUI-Florence-2

If you encounter any issues while using ComfyUI-Florence-2, here are some common problems and their solutions:

  1. Issue: The extension is not producing the expected output.
  • Solution: Check the settings and parameters to ensure they are configured correctly. Adjust the resolution, segmentation accuracy, or bounding box detection settings as needed.
  1. Issue: The extension is not integrating with ComfyUI.
  • Solution: Ensure that you have the latest version of ComfyUI installed. Restart the application and try reloading the extension.
  1. Issue: The output quality is lower than expected.
  • Solution: Use the Florence-2 Large model for higher resolution and better quality results. Adjust the model settings to optimize performance.

Learn More about ComfyUI-Florence-2

To learn more about ComfyUI-Florence-2 and get additional support, check out the following resources:

  • Community forums and discussion groups where you can ask questions and share your experiences with other AI artists.
  • Tutorials and documentation that provide step-by-step guides on how to use the extension effectively. By exploring these resources, you can gain a deeper understanding of ComfyUI-Florence-2 and make the most of its features in your AI art projects.

ComfyUI-Florence-2 Related Nodes


© 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.