ComfyUI Custom Extensions
Browse 8,543 ComfyUI extensions and 65,510 custom nodes.
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)
✨ augment Vectorize — PNG to SVG vectorizer for ComfyUI. Convert raster images, logos, and icons into clean scalable vector graphics. A professional vectorization tool built directly into your ComfyUI workflow via the Augment Studio API with automatic job polling and SVG output. Ideal for logo design, brand asset pipelines, and any workflow that needs crisp vector conversion. Includes built-in flow control trigger and wait nodes for chaining multi-step pipelines. Get your API key at 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.
ComfyUI custom node for upscaling videos using the Remacri upscaler and then downscaling them. (Description by CC)
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
A collection of ComfyUI nodes for cryptography, steganography, encryption, decryption, and tools needed to both make and solve ARGs (Alternative Reality Games) and secret messages.
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.
Universal node hiding extension for ComfyUI. Hide any node on the canvas with a stylish spoiler overlay that disappears on hover.
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
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.
100% of code taken from [a/https://gist.github.com/neggles/ecb6327251a9e274428d07636c727eb9](https://gist.github.com/neggles/ecb6327251a9e274428d07636c727eb9).
Connect your ComfyUI workflows directly to Autodesk Flow (formerly ShotGrid). Browse projects, select shots, assign tasks, and publish versions—all from within ComfyUI.
Custom ComfyUI loaders for timestep-masked T-LoRA inference.
ComfyUI AI prompt generation nodes supporting OpenAI, Anthropic, and LM Studio compatible APIs.
A custom node for ComfyUI that allows temporal switching between prompts.
concatenate all images in floders, concatenate caption txt files for trainning loras.
Full-pipeline virtual try-on and pose transfer ComfyUI custom node, built on Meta's Leffa.
ComfyUI node for converting images to IRC art blocks
ComfyUI conditioning node for reference-conditioned Ideogram 4 LoRAs. Enables inpainting with the Ideogram 4 model.
Experimental file-level Krea2 LoRA merger with conservative handling for gate layers.
A custom ComfyUI node that automatically scales Wan2.1 InfiniTalk video generation to any audio duration without manual segment chaining.
Scoped wildcard selector for ComfyUI. Pick a theme and categories from a bundled 5,200+ entry library with metatype-driven skin tone; get a finished prompt string. No wildcard syntax required.
Nodes:BrevImage. ComfyUI Load Image From URL
EzFlex preset suite for ComfyUI: models combo loader, resolution/latent selector, node switch master & group presets, parameter presets, preview any, prompt helper, media loader/output.
This is a plugin for ComfyUI that adds new Util Nodes and Nodes for easier image creation and sharing.
A ComfyUI extension for using PixelDojo's Flux API to generate high-quality images directly within ComfyUI workflows.
A custom node collection for ComfyUI designed to handle advanced media operations including switching between image and video inputs, face swapping, color matching, and video frame interpolation.
This script adds an automatic batch runner UI to ComfyUI. The underscore in ComfyUI_AutoBatchRunner is a naming error. Please use ComfyUI-AutoBatchRunner.
Nodes:LoraWithMetadata, TypecasterImage.
Custom node to reboot ComfyUI server
Calculator
HunyuanPortrait enthusiast level node pack for experimental and educational exploration
Collapsible Nested Menus and Save Workflow as PNG
ComfyUI custom node for applying PNG watermarks to still images and IMAGE batches.
Pick an LLM role (system prompt) from a dropdown and output it as a STRING for an LLM node's system_prompt. Modes: fixed, increment, or random over a start..end slice, with index/seed control_after_generate to step roles across a batch. Roles are plain Markdown files in roles/; add a .md file and restart to add a role. Node name: Set Role. Located under Add Node > LLM.
ComfyUI nodes for Groq API - chat, vision, audio, tool use, and batch processing
Prompt optimization, local AI forensics, and image provenance for ComfyUI. Includes the Mutant Prompt Optimizer (Word Weight methodology), Mutant Forensic Lab (local FFT/ELA/metadata detection), and Mutant Signature (PNG provenance injection).
Experimental unified-memory-aware DGX Spark / GB10 loader nodes for ComfyUI
This custom node allows users to selectively choose what to add to the generated image's metadata.
Nodes: OTX Multiple Values, OTX KSampler Feeder. This extension provides custom nodes for ComfyUI created for personal projects. Made available for reference. Nodes may be updated or changed intermittently or not at all. Review & test before use.
Prompt Builder, List Pick and String Line Count: text and list utility nodes for building and iterating prompts.
Generate random prompts easily for FMJ using TXT files (1 prompt per file).
Image saving with complete metadata (prompts, seed, software versions) + smart loading.
ComfyUI-native Ulysses sequence-parallel inference for Qwen-Image 2.1 across 1/2/4/8 GPUs, including text-to-image, multi-reference editing, and distributed prefix caching. Requires ComfyUI commit c194dd00 or newer and Linux or WSL2 with NCCL; native Windows is not supported.
Outpaint flat video into fulldome / planetarium shows: domemaster rendering with tilted-venue presets for ComfyUI, on top of the Burgstall Labs 360 outpaint pipeline.
A per channel implementation of the scaled CFG from this paper: [a/https://arxiv.org/abs/2503.18886](https://arxiv.org/abs/2503.18886)
Perpendicular CFG for reducing oversaturation issues with high guidance scale values.
A custom node for randomized prompt generation with __wildcard__ expansion, subfolder filtering, prefix/suffix support, and seed-based reproducibility.
A powerful batch image generation node for ComfyUI using the YK-Banana2 Pro API to generate multiple images in parallel with reference image support. (Description by CC)
Nodes:CharacterManagerNode, FilmGrain, FlipFlopperSameArch
Custom node for generating videos using ByteDance Seedance 2.0 API with support for person and background reference images.
A ComfyUI sampler that boosts detail only in latent regions that are already dense at the moment the schedule activates.
Euler-only middle-block caching for native MiniMax H3 models in ComfyUI.
Group wildcards together for easier character management