ComfyUI Custom Extensions
Browse 8,044 ComfyUI extensions and 59,847 custom nodes.
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.
ComfyUI Node for automated log generation in accordance with the European AI Act
A studio rig for ComfyUI: a tabbed workspace panel, painting with auto masks, wireless control panels, LoRA management, grading and prompt tooling, plus Krea 2 moodboard and identity editing.
Converts booru tags to a format suitable for Waifu Diffusion(or Danbooru based models).
A collection of custom ComfyUI nodes by Ikkyu.
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.
Nest a working ComfyUI run — models, custom nodes, dependency versions and the workflow — and rebuild it byte for byte on any machine.
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.
ComfyUI nodes with easy size/resolution options for image generation.
Highlight each custom node load in the terminal, and show hard/partial import failures in a ComfyUI popup with export tools.
Pen tool editor for ComfyUI: paths, shapes, selections, text, brushes, and multi-image layers. Outputs composite image, mask, stroke layer, alpha image, and path JSON.
NODES:Color Wheel Generator
A ComfyUI custom node for automatically fitting images to standard model dimensions using center cropping, supporting SD, Flux, and Z-Turbo models.
Another mobile frontend for ComfyUI
ComfyUI nodes for daVinci-MagiHuman talking-head audio-video generation with INT8 VRAM modes.
RunningHub MiniMax-H3 audio-video custom nodes for ComfyUI
ComfyUI custom nodes for Retrieval-based Voice Conversion (RVC), including model loading, ZIP upload, voice conversion, and training.
RunningHub ComfyUI nodes for SmartPhotoCrafter automatic photographic image editing.
ComfyUI custom nodes for VoxCPM text-to-speech, voice cloning, multi-speaker generation, and LoRA training.
NODES:Florence2 Coordinates (XY Split), Phi-3.5 Vision Instruct.
It's a ComfyUI wrapper for [a/Dia TTS](https://github.com/nari-labs/dia) by Nari labs, includes a portion of their code used for inference.
Personal custom nodes and tools for ComfyUI.
A modular collection of ComfyUI custom nodes with advanced dependency management and ComfyUI Manager integration.
Multi-view SAM 3D Objects via MV-SAM3D (arXiv:2603.11633). REQUIRES ComfyUI-SAM3DObjects installed and run once first — this pack reuses its environment and weights. Runs the authors' code unmodified from a pinned checkout; one-time 'python scripts/setup_env.py' after install.
Saves images with prompt reference cards - thumbnail + formatted prompt side-by-side with JSON syntax highlighting for easy browsing and organization.
A socket service that helps third-party DCC software maintain long-term image exchange with comfyUI.
ComfyUI-Backup (Description by CC)
ComfyUI extension for loading resources by URL. (Description by CC)
High-performance frame IO nodes (WEBP)
Helps filter and trim image batches for I2V chaining by ensuring consistent face identity and eye openness.
Dynamic resolution selector and advanced resize nodes with real-time feedback.
A ComfyUI custom node extension that provides easy-to-use prompt templates and wildcards for AI image generation.
A powerful custom node for ComfyUI to wake up remote machines via Magic Packets (WOL), resolve their IP addresses efficiently, and monitor their online status.
Select aspect ratio and generate appropriately-sized empty latent for each model
Nodes of EvaluateMultiple1, EvaluateMultiple3... Support the execution of any fragment of Python code, generating multiple outputs from multiple inputs.
Deterministically organize complete ComfyUI workflow graphs: nodes, nested backgrounds, Markdown comments, and ungrouped nodes.
Smart Model Loader for ComfyUI — single node for vision-language models, text LLMs, and WD14 taggers across 8 backends (Transformers, GGUF, vLLM, SGLang, Ollama, llama.cpp, YOLO, WD14). Supports QwenVL, Mistral3, Florence-2, LLaVA, YOLO with multi-task chaining, few-shot training, and auto-download. V3 API + Nodes 2.0 compatible. NVIDIA/AMD/ROCm.
Bridges ComfyUI's native AUDIO type to raw audio tensors (VCAUDIOTENSOR) for MuseTalk, VoiceCraft, and more.
Custom node that allows automatic import and tagging of images generated by ComfyUI directly to the Hydrus (https://github.com/hydrusnetwork/hydrus) API.
Custom nodes for STARFlow text-to-image generation in ComfyUI, including checkpoint loader, text encoder, sampler, and VAE decoder.
Custom nodes for running the Switti text-to-image model inside ComfyUI with support for checkpoint loading, VAE, CLIP encoders, and pipeline building.
Nodes:ImageLoadFromBase64, ImageLoadByPath, ImageLoadAsMaskByPath, ImageSaveToPath, ImageSaveAsBase64.
A custom node for conveniently adjusting the overlay position of two images.
Quickly select preset prompts and merge them
Quickly set up image overlay effects
A collection of custom nodes for ComfyUI
ComfyUI node to pick a camera angle and emit a 'Change camera angle to ...' prompt string.
A collection of custom nodes for ComfyUI
Chat GPT Image Generation Chat Node for Comfy UI
Some nodes to create a preprocessed videos
A voice conversion extension node for ComfyUI based on FreeVC, enabling high-quality voice conversion capabilities within the ComfyUI framework.
This repo make AI-Toolkit FlowMatch scheduler working on ComfyUI.
A ComfyUI custom node for bulk creative prompt generation that takes a seed idea and generates batches of distinct, shaped prompts for LoRA testing workflows. (Description by CC)
This package contains custom nodes for ComfyUI: Image generation using Stable Diffusion and LLM, Uploading and searching images via ChromaDB and MinIO (S3), Integration with CLIP, Ollama, and other tools
ComfyUI node for video super-resolution and frame interpolation using [a/NVEncC](https://github.com/rigaya/NVEnc).
Loads an image and its transparency mask from a base64-encoded data URI. This is useful for API connections as you can transfer data directly rather than specify a file location.
Personalized suite of nodes including a specialized LoRA Detailer, a custom WD14 Tagger, and precise MM-DD-YYYY image saving.
A one-node diagnostic pack. The Env Probe node reports the host ComfyUI runtime so we can decide a wheel/compile strategy without terminal access.
ComfyUI custom nodes for reading CSV rows, with delete and non-delete variants.
A ComfyUI custom node pack that applies a subtle line boil effect to images and videos.
A lightweight ComfyUI custom node that saves images as JPEG (.jpg) files with configurable quality and optional caption sidecar files.
ComfyUI custom node that limits the number of tags in a comma-separated string.
Advanced CPU-based Text-to-Speech nodes for ComfyUI with full parameter control. Forked from ai-joe-git/ComfyUI-Pocket-TTS. Supports temperature, decode steps, EOS threshold, quantization, voice cloning, and 13 language models.
Nodes for Video effects. Zoom In/Out - new features soon.
A custom node for ComfyUI that triggers WinThumbsPreloader every X cycles to ensure Windows thumbnails are generated for your output folders.
Essential video processing nodes for ComfyUI
A ComfyUI custom node used to get one line of string from a multi line string. Search in the manager for `get line`, or `getline` or `get-line`.
This custom node for ComfyUI automatically crops a document by detecting edges, rotates it based on face orientation using MediaPipe, and adjusts it to a target aspect ratio (default 11:14).
A collection of nodes for selecting paths, JSON manipulation, networking (HTTP/Polling), and advanced UI-driven file/list selection.
ComfyUI custom nodes for OpenAI API integration (local supported) with chat completion and image support.
A powerful resolution picker node for ComfyUI with auto-snapping, aspect ratio locking, and megapixels scaling.
Advanced Text Encode node for ComfyUI with dynamic multi-image reference support.
Image passthrough node that holds last value when upstream is bypassed
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.
AIO Pony Node.
One universal node for all 50+ Sequencer AI models. Generate images, videos, and audio (Veo 3.1, Flux 1.1 Pro, Kling, Ideogram, etc). dynamically populates model lists and I/O sockets.
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.
Custom nodes for image preview and saving
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
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.