ComfyUI Custom Extensions
Browse 6,398 ComfyUI extensions and 45,165 custom nodes.
A minimal ComfyUI custom node package for converting images to 3D meshes using TripoSR and rendering them from 8 cardinal/intercardinal directions.
Image-only switch for ComfyUI that checks connected inputs from top to bottom and outputs the first available image. (Description by CC)
ComfyUI custom node for merging multiple text or tag lists with deduplication and custom delimiter support. (Description by CC)
A minimal ComfyUI workflow that turns local videos into clear, human-readable analysis by sampling frames and sending them to Gemini Flash multimodal Video Language Model.
A ComfyUI custom node for rendering diagrams using the Kroki API. Supports 22+ diagram types with high-quality scaling using ImageMagick to convert vector SVG to any resolution.
A custom ComfyUI node for text-to-image and image-to-image generation using Wuli Qwen API. (Description by CC)
A collection of custom nodes for ComfyUI that enhances image processing and cloud storage capabilities.
Nodes:Multi Lora Loader, Random (Prompt), Combine (Prompt), CSV Prompts Loader
Mayo's Custom Nodes, including Aspect Ratio Randomizer and Custom Dropdown
Custom ComfyUI node that uses BRIA RMBG v1.4 for background removal and PNG cutting.
This repository provides a custom node for ComfyUI, leveraging the BriaRMBG model to remove backgrounds from images and output a transparent PNG.
ComfyUI custom node for HeyGen Avatar IV (AV4) video generation
ComfyUI nodes for LTX-2 video generation API
ComfyUI custom node — load AUDIO from a public URL. Bypasses torchcodec entirely. Multi-backend: torchaudio / soundfile / ffmpeg.
ComfyUI custom node — load AUDIO from a public URL. Bypasses torchcodec entirely. Multi-backend: torchaudio / soundfile / ffmpeg.
360° equirectangular image viewer node for ComfyUI
This extension provides a set of nodes that can be used to mask multiple object at once
Protects ComfyUI workflows from network interruptions with automatic retry and fallback
Custom nodes for ComfyUI with Prompt Perfect GPT functionality.
A custom node for ComfyUI that generates images using Google’s Gemini 2.5 Flash Image Preview API.
ComfyUI custom nodes for Chatterbox TTS with multilingual support (23 languages)
ComfyUI custom nodes for converting an anime series title into genre or tag text that can be used in prompt-building workflows.
Small utility nodes for ComfyUI including Anime PromptGen, Load Image Cropped, Pepe Scale Image By, and Stride Scale Size.
Manage secrets that are stored encrypted on your file system. Custom node reads secrets to pass them to nodes without adding them in plaintext to workflow files.
A ComfyUI custom node that renders an interactive 3D RGB color histogram of an image directly on the node, using Three.js.
A collection of nodes to help streamline your ComfyUI workflows
Kuratierte Replicate-Modelle als ComfyUI-Nodes (Bild, Video, Upscale, TTS, Lipsync) + Custom-Node für beliebige Modell-IDs.
A custom ComfyUI node that compares face identity between two images using InsightFace embeddings. Useful for verifying that a generated image preserves the identity of a reference person.
Phota API nodes for ComfyUI — identity-preserving image generation, editing, enhancement, and profile training (photalabs.com).
Custom nodes for ComfyUI by Momo.
A custom ComfyUI node that integrates OpenAI-compatible APIs for prompt generation and enhancement, specifically designed for Stable Diffusion workflows.
Declarative UI Framework for ComfyUI Nodes. Minimalistic base class for creating UI-based audio/text/image nodes.
Comprehensive ComfyUI pack for face-aware detailing with ArcFace matching, per-person LoRA inpainting, color palette generation, and outfit prompt building.
A ComfyUI custom node that automatically snaps input dimensions to predefined resolutions and aspect ratios.
Comprehensive ComfyUI extension pack featuring one-click model installation, real-time download progress, video processing utilities for eye stabilization and character face swapping, and system utilities.
Custom mask utility nodes for ComfyUI - mask fallback and mask area condition.
Audio trimmer with visual Premiere Pro-style timeline for ComfyUI
A collection of custom nodes for ComfyUI focused on variable handling and workflow automation.
Align one pose image to another by matching subject scale and head position for ComfyUI.
ComfyUI node for audio translation with speaker diarization, transcription, and optional dubbed audio synthesis using DramaBox.
Advanced chooser nodes for ComfyUI that let workflows pause for image, audio, or text selection, with optional automatic picking and series helper nodes.
ComfyUI node that loads video by time segments, extracts frames and audio, runs speaker diarization and transcription with optional LLM-based dialogue translation. (Description by CC)
SongGenerationSuite generates complete, structured songs (lyrics + music prompt) and converts them into conditioning compatible with ACE 1.5 audio generation workflows.
A small ComfyUI custom node package for selecting useful still frames from a decoded video frame batch.
Sealed-worker CUDA image nodes (NATTEN, fused-ssim) sourced from prebuilt cuda-wheels
A collection of high-quality texture utility nodes for technical artists and environment designers with precision masking and color extraction for emissive materials.
Custom ComfyUI node for auto-generating JSON prompts with dynamic placeholder templating syntax.
A simple ComfyUI custom node that generates empty latents based on aspect ratio and a user-defined longest side.
Preset nodes to save and use prompt and sampler settings presets for different models.
High-Performance ComfyUI Custom Node Toolkit - Modular and Extensible Architecture A utility toolkit designed specifically for ComfyUI image processing, built with a modular architecture that supports fast extension and the addition of new nodes.
A LLM node with some models. (Description by CC)
Standalone ComfyUI custom nodes for AnyTop - Universal Motion Generation for Any Skeleton Topology.
BGPSeg: Boundary-Guided Primitive Segmentation - Originally from ComfyUI-CADabra
NeurCADRecon: Neural Implicit CAD Reconstruction - Originally from ComfyUI-CADabra
SECAD-Net: Sketch-Extrude CAD Reconstruction - Originally from ComfyUI-CADabra
ComfyUI custom nodes for captioning images via a llama.cpp server with vision support
Fast image and video colorization.
ComfyUI custom nodes for image analysis and preprocessing (V3 API)
A ComfyUI node for patching images using a difference detection algorithm. It detects changes between two images (original and patched), creates a mask of the differences, and merges them back together with configurable blending.
Smart resolution scaling and mixing capabilities for ComfyUI. (Description by CC)
Peek into ComfyUI sampling loops - decode intermediate latents using a VAE during SamplerCustomAdvanced execution
ComfyUI custom nodes for the Pruna API
ComfyUI custom nodes for Baidu Unlimited-OCR model
ComfyUI nodes for splitting/stitching AV latents in LTX video and calculating resolution for staged upscale. (Description by CC)
Utility nodes providing quality-of-life features for interaction with vlo, including memory loaders for media handling.
A small utility node for ComfyUI that provides a node navigator to pan the canvas to any node by ID for quick navigation in large workflows.
Custom nodes for handling fisheye camera distortion in ComfyUI inpainting workflows.
A sophisticated multi-line text node for ComfyUI that provides weighted autocompletion, interactive pill-based tag management, and smart randomization features.
A collection of custom nodes for ComfyUI to split an image into overlapping tiles and stitch them back together seamlessly.
A LoRA stacker for ComfyUI with on-node editor, sync capability between loaders, and folder-grouped search picker.
Drop-in replacement for ComfyUI's SaveImage that writes rich multi-format metadata into PNG files compatible with A1111/CivitAI, with unlimited image input slots and automatic resource hash linking.
Nodes:load images (queue tools). tools made for queueing in comfyUI
Compare your workflow's output against a fixed reference image with a hover swipe slider.
Easily Load Your Frequently Used Prompts in ComfyUI With ComfyUI Template Loader, managing and reusing your favorite prompts has never been simpler. Save time and streamline your workflow by loading your go-to templates with just a few clicks!
Maintenance utility nodes for ComfyUI that scan and repair prompt library LoRA references and manage library entries with pattern-based filtering.
Photoshop-like layered canvas editor for ComfyUI. Multi-layer compositing, masking, blend modes, outpainting, with BiRefNet background/person removal. Forked from Azornes/Comfyui-LayerForge.
ComfyUI text nodes. Pre (preprocess comments, random, and de-emphasis), Show (show and persist text), and Debug (show and persist weights).
A simple custom node for ComfyUI that allows you to compare two images (or batches of images) side-by-side within the UI.
Nodes:Advance Aesthetic Score
Standalone bundle for the single-pose character clone workflow built on Qwen-Image-Edit.
Collection of quality-of-life ComfyUI nodes including a text file loader for parsing descriptions and managing prompts without manual copy-paste. (Description by CC)
Custom nodes for ComfyUI by Rathius
A set of nodes for batch processing of text and images.
Consolidated collection of custom ComfyUI nodes with LLM integration (Claude, Gemini), WaveSpeed API support, and utility nodes for resolution presets and dynamic prompts. (Description by CC)
Custom ComfyUI node for integrating Claude API with image and text capabilities.
Custom ComfyUI nodes for integrating WaveSpeed AI API for image and video generation.
A custom node for ComfyUI that allows you to create lists of prompts with dynamic input count. Add or remove prompt inputs on the fly without creating multiple nodes.
FFmpeg-based custom nodes for ComfyUI that convert between videos and frame batches.
Local LLM chat nodes for ComfyUI, with a clean handoff path to downstream prompt optimization.
A standalone ComfyUI node for loading samplers and providing their names as string outputs.
Modern 3D Processing Nodes for ComfyUI - Optimized for CUDA 12.8 + PyTorch 2.9.0
Speech-God: expressive character-dialogue TTS suite for ComfyUI. F5-TTS / Fish Speech engines, voice cloning, emotion acting, multi-character scripts, character database, alternate takes, post-processing and export.
Converts booru tags to a format suitable for Waifu Diffusion(or Danbooru based models).
Fast safetensors loaders for DGX Spark that use GPUDirect for zero-copy transfers, supporting model and checkpoint loading with VRAM management.
InstantTensor-backed variants of ComfyUI's built-in model loader nodes for CUDA-only devices with streaming support for large models.
A unified file loader and saver for ComfyUI that fixes three long-standing pain points: cross-source navigation in one node, persistent uploads, and saving to input directory.
Custom ComfyUI nodes for direct image generation and editing with OpenAI, Gemini, and OpenRouter API providers without extra account flows.
ComfyUI Easy Loaders is a set of custom nodes designed to make loading models (Checkpoints & GGUF) smarter and more convenient.
Clean workflow routing nodes for ComfyUI. Say goodbye to spaghetti connections!
A physics-based film grain synthesis plugin that brings authentic film grain to your ComfyUI workflows.