ComfyUI Custom Extensions (5699)
Search across 5699 ComfyUI extensions and 40672 custom nodes
ComfyUI-Owlv_Nodes
A collection of custom utility nodes for ComfyUI, providing a variety of practical mini-tools with multiple functions.
comfyui-timm-backbone
ComfyUI Timm Backbone Nodes is a custom node set that enables you to load and use pre-trained models from the [a/timm](https://github.com/huggingface/pytorch-image-models) library within ComfyUI workflows.
ComfyUI-ResizeZeptaPayload
Resize a batch of trajectories or images
ComfyUI-ZeptaframePromptMerger
Custom node that merges general and subject-specific prompts
ImagePromptBatch
A simple comfyui Node for Loading images and thier prompts
Comfy-Firefly
Custom ComfyUI node for generating images using Adobe Firefly Services API v3 with automatic authentication and standard tensor output.
ComfyUI Load Image From URL
A ComfyUI custom node that allows you to load images directly from URLs or local file paths. This node provides a convenient way to import images into your ComfyUI workflows without manually downloading them first.
ComfyUI-ImmichUploader
Upload images (directly from your graph) and files (e.g., videos written to disk) to Immich.
ComfyUI-CartesiaTTS
Node for Cartesia Sonic-3 that calls the `/tts/bytes` endpoint and returns: file_path, bytes, url
Claude Prompt Generator
Node that generates prompts using Anthropic Claude API.
ForgeAI-HeartMuLa
ComfyUI custom nodes for HeartMuLa AI music generation - optimized for 16 GB GPUs
comfyui-lora-tag-hash-metadata
ComfyUI node that converts <lora:name:weight> tags into Civitai-friendly Name:HASH:Weight metadata strings.
Resource Monitor
A ComfyUI-native live resource monitor and snapshot node
ComfyUI-PD19Anime-Nodes
A powerful ComfyUI node suite featuring the Advanced Prompt & Image Loader (Multiple) node, designed for batch extracting and saving image prompts. Automatically reads prompt information from multiple images and passes it to other nodes for processing, plus includes other workflow utility nodes.
ComfyUI-DPIR
A dpir/DRUnet inference node for ComfyUI
ComfyUI-BananaForge
Gemini-powered image generation for ComfyUI supporting text-to-image, image-to-image, and batch processing with flexible API configuration. (Description by CC)
Doom_Flux_NodePack
A set of nodes that improve the work with the Flux model
ComfyUI-HunyuanImageLatentToVideoLatent
A ComfyUI node which copies a given latent's samples tensor along the time axis ((length - 1) // 4) + 1 times to form a longer latent (see EmptyHunyuanLatentVideo's implementation for why this specific number of copies is used) and then prepares a noise_mask tensor of the same shape such that the value of the mask for a given time step is given by the function at https://www.desmos.com/calculator/vhw74mr1vh.
ComfyUI-Custom-Node-Config
This project is a custom node plugin for ComfyUI that provides a form node for configuring and saving parameters related to LLMs (such as OpenAI, Kimi, DeepSeek). Users can input information such as API Key, Base, Version, and Model through the node. The node will automatically save the configuration to a local file and set it as environment variables, making it convenient for subsequent use.
PiePieTweaks
Tweaks and simple nodes for usability and common needs
MF PipoNodes
Utility nodes for ComfyUI workflows: randomization, text processing, logging, and math operations.
ComfyUI_OpenCV
OpenCV nodes for ComfyUI
ComfyUI-LikeSpiderAI-SaveMP3
A custom ComfyUI node that saves input AUDIO as .mp3 using ffmpeg.
ComfyUI-Visual-Image-Crop
Interactive image crop node for ComfyUI with in-node crop rectangle, drag-and-drop image loading, numeric controls, and aspect-ratio helpers.
ComfyUI-AlphaFlatten
This node takes a batch of images with alpha channels (RGBA format) and combines them into a single image, respecting the transparency of each layer. It's particularly useful for compositing multiple masked elements (like faces) into a single image.
ComfyUI-WorkflowGraphics
Embed images directly in your workflow JSONs
ComfyUI-LTX-GapFill
A ComfyUI custom node that brings the "Fill with Video" AI prompt suggestion feature from LTX Desktop into ComfyUI workflows using Google Gemini 2.5 Flash.
comfyUI-PL-data-tools
Image data check, filtering and augmentation tools for ComfyUI 🔬
AssetThingie
Asset management - browse/download from civitai and manage loras/checkpoints
comfyui-zegr
comfyui share models to oss conveniently.
ComfyUI-Cadrille
Cadrille: Multi-modal CAD Reconstruction - Originally from ComfyUI-CADabra
ComfyUI-CameraPack
Camera utilities for ComfyUI. Convert between camera formats (DA3 extrinsics/intrinsics to Load3DCamera for Preview3D).
ComfyUI-PainterVideoInfo
Lightweight video information extraction node for ComfyUI that extracts video metadata including frame rate, frame count, width, and height. (Description by CC)
CSV Styler
Repository contains CSV Styler - custom node for ComfyUI. It loads styles from styles.csv file (Automatic1111 Web-Ui styles.csv format) and combine them with provided positive and negative prompt. NOTE: 'styles.csv' should be placed in ComfyUI root directory (near main.py).
comfyui_color_detection
This plugin adds functionality to ComfyUI for detecting yellow tones in images, making it particularly useful for skin tone analysis and image color evaluation.
ComfyUI Assistant Node
A custom ComfyUI node that integrates with the OpenAI Assistants API.
Qaz Tools
Personal ComfyUI custom node toolkit — dynamic prompts, utilities, and more.
comfyui-ideogram4-bbox-editor
A ComfyUI custom node that renders a visual bounding-box / caption editor on the node itself and outputs the assembled Ideogram-4 caption (v15 format) as a JSON string.
Redial Discomphy - Discord Integration for ComfyUI
A custom node for ComfyUI that enables direct posting of images, videos, and messages to Discord channels. This node seamlessly integrates your ComfyUI workflows with Discord communication, allowing you to automatically share your generated content.
Claude CLI (Vision+Text)
Call the local `claude` CLI from ComfyUI for vision+text or text-only completions. Uses your existing `claude login` OAuth (no API key required). Supports UUID session reuse for prompt-cache savings, with session token-usage tracking. Additional utility nodes: `Split Image Batch to List of Image Batches` (takes a large incoming batch and splits it into a list of smaller sub-batches with start/end index outputs, so you can send N images at a time — e.g. pairs — to the Claude CLI node along with their original batch indices for tracking), `Indexed 2x2 Grid from Batch`, `Select Images (Bounds Safe)`, and `Image Batch Current Index`. Optional headless API-key mode.
Unified Conditioning Merge (with timestep ranges)
ComfyUI custom node: range-aware Concat/Combine/Average for CONDITIONING that correctly carries start_percent/end_percent across both inputs. Single unified node with mode dropdown, dynamic 1..N input slots, per-slot weights, and timestep-range intersection.
Pixel Palette Art
Comfyui custom node: Set of tools for pixel art palette.
zhihuige-nodes-comfyui
Nodes: Combine ZHGMasks, Cover ZHGMasks, ZHG FaceIndex, ZHG SaveImage, ZHG SmoothEdge, ZHG GetMaskArea, ...
rcsaquino/comfyui-custom-nodes
Nodes: VAE Processor, VAE Loader, Background Remover
comfyui-tensortrap
Security scanner for ComfyUI workflows, custom nodes, and model files
ComfyUI-Artist-Selector
A useful comfyui node named LoadArtistTag for selecting artist tags, including 1000+ single-artist tags and 300 mixed-artists tags.
ComfyUI-OneShotOutputs
A minimal ComfyUI extension that lets you mark any node to discard its output from cache immediately after all downstream nodes have consumed it.
ComfyUI_Text_Line_Combine
Combines texts line by line to a single text
ComfyUI-RE-CustomUtils
A collection of custom nodes for ComfyUI.
comfyui-ricklove
Nodes: Image Crop and Resize by Mask, Image Uncrop, Image Shadow, Optical Flow (Dip), Warp Image with Flow, Image Threshold (Channels), Finetune Variable, Finetune Analyze, Finetune Analyze Batch, ... Misc ComfyUI nodes by Rick Love
Rikannodes
kijai ComfyUI-PromptRelay with fps and max frame output
Diana - Interactive Assistant
🧝 Interactive assistant that lives in your ComfyUI workspace. Reacts to queue events with animated sprites, voice lines, and text bubbles. Features multiple personalities: Diana (calm), Kitty (cute), Kerrigan (dark). Includes audio toggle, idle timer, and smart error detection.
ComfyUI-Floyo-Flux2-API-node
ComfyUI node integrating Black Forest Labs FLUX.2 [pro] API via Floyo for text-to-image and image editing. (Description by CC)
riversidenodes
A custom node to resize your image to model-specific resolution
ComfyUI-RizzNodes
RizzNodes for ComfyUI Welcome to RizzNodes, a collection of custom nodes for ComfyUI designed to streamline various workflows, from loading images and models in batches to dynamic prompt generation and memory management.
ComfyUI-RogoAI-PromptRelay
Prompt Relay custom nodes for Wan2.2 I2V and LTX-Video 2.3 that connect multiple scenes in latent space to reduce character drift and improve consistency. (Description by CC)
ComfyUI Batch BBox Detector
Process batches of images (e.g., video frames) with ultralytics bbox detection in ComfyUI. This custom node package extends the standard BboxDetectorCombined to handle batches efficiently, making it ideal for processing 300+ video frames.
Promptcraft
Dynamic prompt generation with {A|B} variants, __wildcard__ files, and ${var} variables
Google Font Text Image Node for ComfyUI
This custom node provides a powerful and flexible way to create images from text with advanced typographic controls. It's an ideal tool for generating inputs for Typography, creating titles and watermarks, or producing font specimens for multimodal models to analyze and generate.
comfyui-maya1-tts
High-quality text-to-speech ComfyUI custom node powered by Maya1 model
ComfyUI_PoseAlign
A custom node for ComfyUI that provides pose alignment functionality.
Ephemeral Preview Tap
A lightweight IMAGE preview tap node that sends an in-memory JPEG contact sheet without writing temporary preview files.
ComfyUI-GMImageSaver
GraphicsMagick-based direct JPEG saver node for ComfyUI. Saves IMAGE tensors directly as JPEG without intermediate PNG files. JPEG-only, previewless, label-aware, and useful for organized batch/inventory workflows. NOTE: GraphicsMagick must be installed separately and available via GM_PATH or PATH.
ComfyUI-LightQueueCounter
Lightweight custom node for ComfyUI that displays backend queue count during workflow execution with minimal performance impact (0.004s overhead) and flexible display modes. (Description by CC)
ComfyUI-PromptRandomChoice
Lightweight random selection node for rapid prompt variations with independent multiple-node support and wildcard processing capabilities. (Description by CC)
ComfyUI-Secrets
Simple node to manage API keys and secrets for OpenAI, Anthropic, OpenRouter, Stability AI, etc... Allows you to keep your secrets out of your workflows. Zero Deps
uber_comfy_nodes
ComfyUI Nodes for misc. use-cases
Comfy_z-sampling
Implementation of xie-lab-ml/Zigzag-Diffusion-Sampling into ComfyUI, tested primarily with Anima video workflows.
ComfyUI-Amage
This repository provides a set of custom nodes for ComfyUI, designed to improve workflow convenience when working with text, image, video, and audio data.
ComfyUI-GeminiImageToPrompt
Imagen descripcion prompt system
ComfyUI.RaccoonAI
Custom nodes for ComfyUI that integrate with the RaccoonAI local AI management system.
Comfy Text Stats
Node: Text Stats (Char & Word Count). A lightweight ComfyUI custom node that takes a text string and outputs character and word counts (INT). Ideal for caption preprocessing, prompt analytics, and dataset workflows.
ComfyUI-Sonic
Custom node that takes an audio mp3 and an image, and creates a lip synced video from them.
ComfyUI Video Reverse
A tool to reverse the frames of video type files (MP4, WebM, WebP, Animated GIF) using ComfyUI. It gets the image batch tensor and returns the same tensor, but flipped.
comfyui-image-labeler
Image labeler for ComyUI
ModelPulse
Track model usage frequency to identify abandoned or underutilized models. Shows usage stats, file sizes, and highlights stale models in a sidebar panel.
ComfyUI Safety Checker
This project provides custom safety checkers for image classification using Falcons AI and CompVis models. The safety checkers are designed to detect and filter out NSFW content from images.
Image Grid Merger
ComfyUI custom node that merges a batch of images into a single grid canvas.
ComfyUI-TeaCache-Lumina
ComfyUI Node Implementation: TeaCache Acceleration Specifically Designed for the Lumina Model
comfyui-civitai-workflow
Load workflow from civitai image.
comfyui-group-selection
Create a new group of nodes.
comfyui-load-image-with-cmd
Load image and partially workflow with javascript.
comfyui-prevent-sleep
Prevent sleep while running ComfyUI.
comfyui-target-search
Move canvas to target on dragging connection.
comfyui-textarea-command
Add command and comment in textarea. (e.g. // Disabled line)
comfyui-textarea-keybindings
Add keybindings to textarea.
Comfyui-ImageAB-Compare
image split comparison horizontally/vertically, real-time mouse interaction to adjust split ratios, bidirectional linkage between slider and mouse, and the ability to export comparison images with precise split lines.
LoRA Helpers
ComfyUI nodes for LoRA training evaluation — XY grid sampling across checkpoints and prompts
Comfyui_SynVow_TeleStyle
ComfyUI video style transfer plugin based on TeleStyle for applying reference image styles to source videos. (Description by CC)
ComfyUI-YuGiOh
Custom ComfyUI nodes to help with creating custom Yu-Gi-Oh! cards and modding the video games
comfyui-encrypt
ComfyUI custom nodes for RSA image encryption using asymmetric cryptography with key generation, encryption, and decryption functions via the cryptography library. (Description by CC)
Skycoder Tools
A collection of useful custom nodes for ComfyUI workflows
comfyui-lmstudio-flux2-prompt-generator-simple
Simple ComfyUI custom nodes for generating FLUX.2-style prompts with a local LM Studio model, with simplified controls optimized for cleaner output.
Slimy_ImageComparer
A/B image interactive comparison node for ComfyUI with multiple comparison modes (A, B, Slide). (Description by CC)
ComfyUI-Camie-Tagger
ComfyUI node integration for the Camie tagger v2 model from Hugging Face for image tagging. (Description by CC)
DVA_Qwen_TTS
High-quality multilingual TTS with voice cloning, emotion control, and support for Qwen3-TTS models (CustomVoice, VoiceDesign, Base).
ComfyUI-SmartImageTools
NODES: Various nodes for image manipulation
ComfyUI-FaceKeypointsFilter
ComfyUI custom node that selectively filters facial keypoints from DWPose/OpenPose output, allowing selective disabling of face parts (chin, eyebrows, eyes, nose, mouth outer/inner contours) for ControlNet workflows. (Description by CC)
ComfyUI-Qwen3VL-NightShift
A ComfyUI custom node for multimodal inference with Qwen3VL vision-language models accepting text, up to 4 images, and video in one node.
comfyui_meme_maker
Meme Maker Node for ComfyUI.