ComfyUI Custom Extensions

Custom node for ComfyUI that generates images using Google's Gemini API directly within ComfyUI, supporting resolutions up to 4K.

A collection of utility nodes for image processing, workflow management, and generation metadata tracking.

Custom node for converting metadata-enriched PNG images from fusenchat into ComfyUI prompt text chips with drag-and-drop reordering capabilities.

A dynamic ComfyUI custom node that reads prompts from individual sheets/tabs within a local Excel (.xlsx) workbook.

Professional e-commerce main image prompt generator for motorcycle equipment (helmets, riding gear, protective gear) with 9 design styles and 2 canvas ratios. (Description by CC)

Filters and rewrites gendered vocabulary in Danbooru tags and natural language prompts to fix female-biased output from models like TIPO.

A ComfyUI custom node that performs positional placeholder substitution on a template string with {0}, {1}, {2}, etc. placeholders.

Does the same thing as comfyui_image_metadata_extension but is slightly more modern, sending the output to Telegram and downloading unnecessary metadata at the same time.

A custom ComfyUI node for translating long texts with automatic chunking support.

Batch-aware character centering for ComfyUI. Given a character sheet (multiple angles), scales every image so the face ends up at the same size and canvas position — including back-view angles, via a silhouette fallback tied to the batch's face scale. Includes a Fine-Tune node for per-image zoom/nudge with a live canvas preview, and an Anime Face Detect node for crop+mask using lbpcascade_animeface.

Character animation nodes for ComfyUI: walk cycle detection, face-based centering, and sprite strip assembly.

Single ComfyUI node to securely download image/audio files from a URL.

RunNode prompter nodes for ComfyUI

Connect the current ComfyUI canvas to a local MCP client

A real-time bidirectional bridge between Adobe Photoshop and ComfyUI for seamless image generation and editing directly in your layer stack.

Simple node to show ANY output text in the CMD console with color options

Shows Total Time Taken Only for the VAE Decode. Also shows the Timestamps for VAE start/stop.

A pure backend custom node/plugin for ComfyUI that records execution time for each node in a workflow and maximum device usage statistics.

ComfyUI nodes for VOID — Video Object and Interaction Deletion (netflix/void-model)

Nodes for YuE2 ABC scores: change its tempo, search for a score that fits a target song length, check a score's length, and repair meter glitches.

Load media (image/video/audio) from remote URL

LoRA loader nodes with preview images: a single LoRA loader and a Power-LoRA-Loader style multi-LoRA stack, with hover previews in the LoRA picker.

Connect a new link from out of screen.

Set global prompts using note node.

Load new workflow after mask editing.

Store settings by model.

Print model metadata on note node

Fix node to top.

Add commentify, indentation, auto-close brackets in textarea.

This custom node allows you to select a LoRA file from the models/loras directory (including subfolders), automatically load training tags from metadata or Eagle MEMO, set strength, and optionally display a preview image.

Native ComfyUI nodes for Zyphra ZONOS2 text-to-speech and voice cloning with AIMDO memory tracking and emotion conditioning

a powerful image concatenation tool for ComfyUI, with True Alpha Channel Support and Multiple Image-block Fill Modes(V1.1 add 1 images input port and 2 draw modes).

A completely rewritten and enhanced custom node for ComfyUI that integrates with Black Forest Labs FLUX API, providing seamless access to FLUX's image generation and finetuning capabilities with improved reliability and user experience.

Fetch a fresh image straight into your workflow from 8 daily/random sources. Useful for prompt testing, style references, daily-image automations, or just kicking off a workflow with something interesting.

ComfyUI custom node for adding recolorable watermarks to images with interactive in-node editor for color picking, positioning, scaling and rotating. (Description by CC)

checkpointloader extension: auto add VAELoader and CLIPSetLastLayer, with checkpoints info manager(right click the node)

Custom nodes for ComfyUI with Ollama integration for LLM chat, vision analysis, and utilities

Custom ComfyUI node for cleaning raw Qwen Thinking VLM output before it is sent into image-generation prompt conditioning.

NODES: Audio Recorder, Line Counter, Increment INT, Image Processor, Load 3D Mesh From Outputs

FaceCanon scales a detected face to a canonical pixel size, lets you run your favorite face detailer at that sweet spot, then maps the result back into the original image with seamless blending. The payoff is consistent face style no matter the input resolution or framing.

EXIF image metadata viewer supporting multiple ComfyUI platforms with prompt extraction and visualization capabilities. (Description by CC)

Comfyui server file browser for uploading & downloading files to server from browser

Save prompt history and reselect

A collection of utility nodes for ComfyUI that enhance workflow capabilities with advanced loaders and processing tools.

Custom node for finding files and showing their contents

A very simple ComfyUI node to remove item with mask.

LlamaCpp integration node for running local language models in ComfyUI. (Description by CC)

A node for randomly fetching Pokemon Infinite Fusion sprite and prompt snippet and add to your workflow.

Proof of concept for quantization handler registration. (Description by CC)

Advanced wildcard control with seed-based selection, LoRA stack support, and utilities.

Advanced image and video loading nodes for ComfyUI with comprehensive animation support, batch processing, and flexible frame selection capabilities.

SD HeartMuLa - Multilingual AI music generation nodes for ComfyUI. Generate full songs with lyrics using the HeartMuLa model family. Supports English, Chinese, Japanese, Korean, and Spanish with song structure control via section markers and style tags.

Several nodes that attempt to extract metadata and raw text information from Gen AI models.

Custom nodes for ComfyUI that help iterate over and save image/caption datasets, useful for preparing training data for fine-tuning diffusion models.

ComfyUI custom nodes for Chutes.ai video generation API

Fixes ComfyUI's case-sensitive dropdown sorting so all combo widgets sort A→Z, case-insensitively.

Cyberpunk/Spy-craft steganography nodes for ComfyUI. Hide secret text messages inside AI-generated images using LSB (Least Significant Bit) steganography. Features encryption with optional password key. Nodes: StegoEncode (hide text), StegoDecode (reveal text).

Load numbered videos from a folder for batch workflows. Supports skip-missing mode for sequences with gaps.

A raw, flexible wrapper node for running local Llama binaries directly within ComfyUI with full control over flags and support for experimental models.

Unified loader nodes with folder organization support for checkpoints, LoRA, VAE, and diffusion models

AsyncDiff node for ComfyUI

[a/Distrifuser](https://github.com/mit-han-lab/distrifuser) sampler node for ComfyUI

ComfyUI custom node for generating and controlling random seeds across multiple generations. (Description by CC)

ComfyUI custom node: Load & Resize Image with Mask and Filename output

Save image node for ComfyUI that also writes the prompt as a .txt with the same filename, plus Reveal-in-file-manager, Save Training File (copy image + txt to a folder) and Delete Last Image buttons.

A custom ComfyUI node that receives a text prompt, removes or replaces sentences based on user-defined trigger words, and passes the filtered text to the next node.

Unofficial Venice AI API nodes: every Venice image, image edit (one image or up to 10 references) and video model (prices and censored/uncensored in the model list, per-model durations/resolutions, cheap preview runs, price limit) plus Video Save Plus, Save Image + Prompt TXT and Load & Resize Image + Filename. Needs your own Venice API key. Not affiliated with Venice.ai.

A custom ComfyUI node that batch-processes files from an input folder, removes every sentence containing the word "Watermark", and saves cleaned files to an output folder. Supports dry run and case-sensitive modes. (Description by CC)

Various auxiliary nodes, continue to increase when there is free time

Build a ComfyUI "self-improving" workflow where each render is evaluated by a local vision LLM, which then edits the prompt/parameters and triggers another run.

face detection nodes for comfyui

Nodes:SingleImageDataUrlLoader

ComfyUI custom node that generates pose images from DWPose/OpenPose keypoint data, allowing creation of pose visualizations with selectively filtered body parts. (Description by CC)

Custom ComfyUI node providing comment stripping functionality for prompts with multiple marker styles. (Description by CC)

ComfyUI custom nodes for InfiniDepth — arbitrary-resolution monocular depth estimation.

Generic YOLO-Pose keypoint detector: IMAGE -> keypoints JSON (also to /history).

NODES: Mobile SAM Model Loader, Mobile SAM Detector, Mobile SAM Predictor

ComfyUI custom node for Kie Nano Banana 2 image generation with optional reference images.

A ComfyUI custom node for saving images in various formats

A powerful ComfyUI custom node for saving images with flexible custom metadata fields embedded in PNG files.

Custom ComfyUI nodes for the INDG toolset including flexible image batching, path utilities, and memory cleanup.

Nodes: Ultimate Concat (Mobile), Send Notification (Mobile), Settings Launcher (Mobile), Settings Launcher Outputs (Mobile)

Ported from ComfyUI-IF_Gemini to support Gemini 3.0 API calls. Please NOTE: Open Router Functionality has been removed.

Custom ComfyUI node: switch between two inputs from an optional boolean condition, with graceful handling when inputs are missing.

Node for scheduling conditioning strength while preserving non-floating tensors such as token ids.

Frontend-only nodes that publish or read many named variables at once: a rack of setters, and a rack of getters.

A node for ComfyUI that provides a convenient way of resizing or cropping an image for diffusion tasks.

A simple node for ComfyUI that rotates or resizes the input latent to common orientations.

Adds windowed, curved shift control for Flow Matching samplers (SD3-style / flow schedules). It is a drop-in replacement for Comfy's included ModelSamplingSD3 node.

A node for ComfyUI that picks from `input_a` and `input_b` based on the given `chance`.

Lightweight repository containing an independent CCIP inference module for anime character feature extraction, pairwise difference calculation, and clustering. (Description by CC)

A minimal ComfyUI custom node plugin to load and run a CCIP adapter.

Pick a megapixel budget and aspect ratio; get the closest usable resolution.

Nodes to enable easy selection of image/video sizes (width/height) and int/string selectors

Custom nodes for ComfyUI that enable video generation using ByteDance's Seedance model via [a/Fal.ai](https://fal.ai/).

This custom node saves metadata when I explore images. It creates a sidecare json file beside the image file.

This custom node builds a new LoRA or patch file relative to a finetuned model, computing weight differences and writing results as standard LoRA or exact diff patch files.

Custom nodes for ComfyUI that combine LoRA loading with prompt text injection and a boolean enable/disable switch.