ComfyUI Custom Extensions
Browse 9,446 ComfyUI extensions and 73,215 custom nodes.
a ComfyUI extension to organize workflow nodes into a clean, flowchart-like layout with same-type nodes aligned and connected nodes flowing left-to-right
Simple and efficient custom node for overlaying customizable text onto images with font support, multi-language ready, and full position/color control.
ComfyUI nodes for creating images with the look and feel of various film stocks.
Transforms a string by dynamically evaluating Python code written in the node
A creative alternative to dynamicprompts
An optimized, pure PyTorch implementation of the Ideogram 4 logit-normal timestep scheduler for ComfyUI.
ComfyUI UNO Nodes is a collection of nodes for ComfyUI that allows you to load and use UNO models.
ComfyUI custom nodes integrating three Chinese AI image generation platforms (Hi Dream, Douban, NanoBanana) supporting text-to-image and image-to-image generation with parallel processing and robust error handling. (Description by CC)
A comprehensive, all-in-one suite for seamlessly integrating Large Language Models (LLMs) like Google Gemini and OpenAI (ChatGPT) directly into your ComfyUI workflows.
OpenClip read/write nodes for ComfyUI - file exchange with Flame
multiGPU batch-parallel upscaling nodes for ComfyUI.
This repository contains a custom node for ComfyUI that converts text into a JSON object. The node is designed to be user-friendly and supports multi-line JSON input.
A single multiline prompt textbox with literal STRING output for native MiniMax H3 Reference to Video workflows.
NanoBanana2 is a custom ComfyUI node for Google Gemini image generation models.
Inline help panel for ComfyUI Nodes with remote HTML/Markdown support.
Extension widgets for ComfyUI
Tile-based upscaling nodes for ComfyUI — Nano Banana 2 compatible
ComfyUI custom nodes wrapping the Lightricks LTX REST API (text-to-video, image-to-video, retake/video-to-video, and HDR EXR video-to-video).
Batch size above 1 for MiniMax H3 Image, P-H3-Image and MiniMax H3 video: runs the model once per batch item, and saves batched video as separate clips with their own audio.
Progress nodes for your ComfyUI canvas: step, speed, time running, time left and VRAM, in a node you place anywhere on your graph.
A custom ComfyUI node that randomizes tag weights for text prompts. Useful for dynamic prompt generation or creative experimentation in AI image workflows.
ComfyUI nodes for 3D visualization.
ComfyUI node package for BYOK (bring-your-own-key) access to external generative APIs: Gemini, Veo, and more via LiteLLM.
Enhance GLB 3D models with realistic materials, smart emissive elements, and procedural normal maps
This is a pack with some handy nodes for ComfyUI.
Text-to-motion animation pipeline for ComfyUI: SOTA motion models (MDM, priorMDM, MoMask, Kimodo) in isolated Docker containers, plus resampling, IK cleanup, character rigging, and GLB/FBX export nodes.
ComfyUI custom nodes for ByteDance's Lance—unified 3B multimodal model supporting text/image/video generation, editing, and understanding in single framework.
ComfyUI nodes wrapping pyiqa (IQA-PyTorch) quality metrics: one loader over the whole registry, generic FR/NR score nodes, plus dedicated nodes for Q-ReAlign, FGResQ, FID and CLIP Score.
load and download YouTube videos from URL's for quick and easy use for vid2vid cases.
Kokoro is an open-weight TTS model with 82 million parameters.
Interpolate sdxl latents using slerp with and without a mask. use with unsample nodes for best effect
This extension provides PSD layer saving functionalities with mask support for ComfyUI.
ComfyUI nodes for Qwen3-TTS: voice design, voice library, segmented generation
A collection of efficient workflow nodes for ComfyUI with advanced sampling, seed management, temporal prompt processing, and workflow optimization tools
1 node to have control over your workflow.
ComfyUI nodes wrapping LongCat image generation and editing pipelines with text-to-image and multi-image edit flows using diffusers framework. (Description by CC)
Utility nodes for ComfyUI: Prompt Stack, Picker, Search & Replace, and Labeled Index.
ComfyUI Qwen 3.5 Prompting nodes (captionate image, improve prompt, etc)
ComfyUI nodes for detailed region inpainting with smart cropping, upscaling, and seamless compositing back into the original image.
ComfyUI node that lets the user pick a folder on their own machine and, on every workflow run, uploads exactly one file from it to the server.
ComfyUI prompt enhance nodes and string utilities
Backend liaison services for SugarSubstitute and ComfyUI.
Ensemble stem separation with UVR and SAM Audio, curated models, Audio2MIDI, Stem save node, waveform render for IO nodes, other utility nodes. Dependencies are not installed automatically. Install audio-separator and basic-pitch per INSTALL.md.
A python port of pixelit by giventofly.
Qwen2 Nodes for ComfyUI. I needed to run Qwen2 on ComfyUI to use it in my workflow for batching images and captioning and none of the implementations I found on the web worked the way I wanted.[w/May contain bugs.]
Dynamic All-In-One Guider/Scheduler/Sampler nodes for custom sampling
Legacy prompt control nodes. These exist only to allow old workflows to run
A set of base64 input and output nodes for a custom API using ComfyUI
A collection of personal ComfyUI nodes designed to enhance and automate workflows.
Small ComfyUI addon that provides segment-safe utilities for Comfy-Org LTX video nodes.
One master, every deliverable. Protected crops, optional conformed film finish, named delivery sets for ComfyUI.
✨ Augment Upscale — Logo and image upscaler for ComfyUI. Upscale logos, icons, and brand assets to high resolution with sharp, clean results. A professional alternative to Magnific AI built directly into your ComfyUI workflow. Supports 2x upscaling via the Augment Studio API with automatic job polling and tensor output. Ideal for logo design, brand asset pipelines, print-ready artwork, and any workflow that needs crisp detail-preserving enlargement. Includes built-in flow control trigger and wait nodes for chaining multi-step pipelines. Get your API key at [a/augmentstudio.app/pricing](https://augmentstudio.app/pricing)
A simple, robust node for talking to any Ollama server (local or LAN) from ComfyUI. Vision, IMAGE-batch support, thinking mode, auto model discovery.
A node for ComfyUI to downsample framerate ie. from 48 to 24.
Nodes for using Orpheus-TTS in ComfyUI
Live elapsed timer in the ComfyUI menu bar while your workflow runs
A ComfyUI extension that displays the preview full-size in a floating window while any node is running.
Nodes:Image cropping tool
Custom ComfyUI nodes for DOGMA AI video workflows.
Custom node to manage A1111's styles.csv via an A1111-inspired UI.
character nodes for characters from various anime shows and comics
Professional ACES and EXR workflow nodes with OCIO 2.1 support and sequence loading.
SuperAgent inside ComfyUI: multi-provider AI assistant with live canvas workflow automation.
NODES: Vaja Synthesis Api, ShowText
A package for intelligent image scaling, aspect ratio adjustments, metadata extraction, and video frame processing for Wan 2.1 vid2vid/img2vid workflows with Pony/SDXL models.
GradientBlurNode is a custom node for ComfyUI that allows for gradient-based image blurring. This tool provides precise control over the direction, intensity, and distribution of the blur, making it ideal for creating smooth transitions, focusing attention on specific parts of an image, or adding artistic effects.
ComfyUI node for AI image generation and chat integration (Description by CC)
A custom ComfyUI node for loading images directly from URLs for AI image generation workflows.
A custom implementation of the Qwen 3.5 Vision-Language model for the ComfyUI framework with text, image, and video inference support.
Variation on LTX 2.3 scheduler with exposed exponent parameter for decoupled schedule hold and midpoint slope.
ComfyUI custom node that reuses the KJNodes Ideogram 4 visual box editor pattern for Z-Image-Turbo regional prompting.
Used to convert workflow node settings into AIV mini-program parameters.
ComfyUI wrapper for SMC-CFG (Sliding Mode Control) classifier-free diffusion guidance from CVPR 2026 research.
A ComfyUI custom node set that generates adversarial examples using a pretrained ResNet18 classifier.
A custom ComfyUI node that reconstructs an image from only 10% randomly sampled k-space (Fourier) coefficients using rigorous Compressed Sensing theory.
A ComfyUI custom node package that aligns and stitches two images using Cross-Bimagnitude, the magnitude component of the Cross-Bispectrum from Higher-Order Statistics (HOS).
ComfyUI Custom Node for converting images to frequency spectrum visualizations using FFT
A ComfyUI custom node pack for 2-D Discrete Cosine Transform (DCT) based frequency-domain filtering with interactive spectrum mask editing.
Line Segment Detector combined with DCT compression for extracting and smoothing curves in ComfyUI image processing. (Description by CC)
ComfyUI custom node computing visual saliency map using eigenvalues of local Quaternion cross-spectral matrix from Quaternion Fourier Transform. (Description by CC)
ComfyUI custom node for FFTNet language model inference using efficient FFT-based global token mixing as an alternative to self-attention. (Description by CC)
A custom ComfyUI node that applies Fourier Domain Adaptation (FDA) between a target image and a reference image.
A ComfyUI custom node that computes the Fractional Fourier Transform (FrFT) of an image and outputs its magnitude spectrum.
FUDA: Fourier-based Unsupervised Domain Adaptation nodes for ComfyUI
A ComfyUI custom node that smooths mask contours using the Fourier Descriptor algorithm.
A ComfyUI custom node that detects corners using Phase Congruency, an illumination-invariant feature detector.
A ComfyUI custom node that detects edges and features using Phase Congruency, an illumination-invariant feature detector based on Fourier components.
A ComfyUI custom node for 2× video frame interpolation using a Fourier-transform-based phase difference algorithm.
A ComfyUI custom node that applies the Phase Stretch Transform (PST) to images. PST is a physics-inspired edge detection algorithm that enhances features by simulating wave propagation through a dispersive medium.
A ComfyUI custom node that computes visual saliency maps from color images using the Quaternion Fourier Transform combined with Spectral Residual method.
ComfyUI custom node that converts color images to grayscale using quaternion mathematics with multiple conversion methods.
A ComfyUI custom node that computes and visualizes the Radial Average Amplitude Spectrum for frequency-domain image analysis.
Precise LAB color recoloring tools for ComfyUI with single-zone, multi-zone, and batch processing capabilities for product images.
ComfyUI Custom Node Package with Logic Nodes, Sigma Utilities, Text Tools, and Image Collage
Use text, image and video models through third-party OpenAI-compatible API relays such as new-api and one-api, with several relays at once. A Relay Manager window adds and tests relays, lists their models and places configured nodes on the canvas. You need your own relay account, and the relay bills your calls. No extra dependencies.
An image source switch node for ComfyUI
A ComfyUI node designed to load the most recent image in a folder
A revolutionary technique for increasing output variety.