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-DanbooruSearcher

ComfyUI Extension: ComfyUI-DanbooruSearcher

Repo Name

ComfyUI-DanbooruSearcher

Author
SuzumiyaAkizuki (Account age: 1891 days)
Nodes
View all nodes(2)
Latest Updated
2026-05-30
Github Stars
0.05K

How to Install ComfyUI-DanbooruSearcher

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

ComfyUI-DanbooruSearcher is an extension for ComfyUI that enables users to search and retrieve images from the Danbooru image board directly within the interface. It streamlines the process of finding specific images by integrating search functionality, allowing for efficient and convenient access to Danbooru's extensive image database.

ComfyUI-DanbooruSearcher Introduction

ComfyUI-DanbooruSearcher is an innovative extension designed to enhance your experience with ComfyUI by providing a fuzzy search method for Danbooru tags. This extension allows you to input natural language descriptions, which can be in either English or Chinese, and it will return corresponding tags from the Danbooru dataset. This tool is particularly useful for AI artists who want to find specific tags without needing to know the exact terminology used in the Danbooru database. By simplifying the process of tag discovery, ComfyUI-DanbooruSearcher helps streamline your creative workflow, allowing you to focus more on your art and less on the technicalities of tag searching.

How ComfyUI-DanbooruSearcher Works

At its core, ComfyUI-DanbooruSearcher uses a semantic search approach to match your natural language input with relevant Danbooru tags. Imagine it as a smart assistant that understands your description of an image and finds the most suitable tags that match your vision. It leverages the BGE-M3 vector model to interpret and process your input, ensuring that even vague or complex descriptions can be translated into precise tags. This process involves breaking down your input into segments, searching for each segment, and then compiling a list of potential tags that best fit your description.

ComfyUI-DanbooruSearcher Features

This feature acts as the semantic search node. You provide a natural language description, and it returns a pool of candidate Danbooru tags. Key parameters include:

  • Text: Your input description, supporting both English and Chinese.
  • Model Path: The local path to the BGE-M3 model. If left empty, the model will be downloaded automatically.
  • Top_k: Determines how many top candidate tags are selected for each segment of your input.
  • Limit: Sets the maximum number of tags to output.
  • Popularity Weight: Adjusts the influence of tag popularity on the final score.
  • Use Segmentation: When enabled, the input is segmented for more comprehensive searches.
  • Show NSFW: Controls whether NSFW tags are included in the results.

This node expands the candidate tag pool by finding related tags from a co-occurrence database. It is designed to work as a retrieval layer in a Retrieval-Augmented Generation (RAG) system, ensuring that the tags provided to a language model are accurate and comprehensive.

  • Search Result: Receives output from the Danbooru Smart Search.
  • Limit: Sets the maximum number of related tags to recommend.
  • Show NSFW: Controls the inclusion of NSFW tags in recommendations.

ComfyUI-DanbooruSearcher Models

The extension relies on the BGE-M3 vector model, which is crucial for processing and interpreting your input descriptions. It is recommended to download this model locally for optimal performance, as it ensures faster processing and reduces dependency on internet connectivity.

Troubleshooting ComfyUI-DanbooruSearcher

Here are some common issues and solutions:

  • Model Download Issues: Ensure you have a stable internet connection if the model is not downloaded locally. Alternatively, download the model manually and specify the path in the model_path parameter.
  • Unexpected Search Results: Adjust the top_k and popularity_weight parameters to refine the search results. Experiment with enabling or disabling use_segmentation based on the complexity of your input.
  • NSFW Content: If NSFW tags are appearing unexpectedly, ensure that the show_nsfw parameter is set to False.

Learn More about ComfyUI-DanbooruSearcher

To further enhance your understanding and usage of ComfyUI-DanbooruSearcher, consider exploring the following resources:

  • Online Demo: Try the DanbooruSearch on HuggingFace for a hands-on experience.
  • Community Forums: Engage with other AI artists and developers to share tips and solutions.
  • Documentation and Tutorials: Look for tutorials that explain the integration of ComfyUI-DanbooruSearcher with other tools like the ComfyUI-NewBie-LLM-Formatter for a more comprehensive workflow. By leveraging these resources, you can maximize the potential of ComfyUI-DanbooruSearcher in your creative projects.

ComfyUI-DanbooruSearcher 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-DanbooruSearcher detailed guide | ComfyUI