ComfyUI Custom Extensions
Browse 9,420 ComfyUI extensions and 73,215 custom nodes.
A fork of ComfyUI-See-through by @jtydhr88, adding a custom node with the option to skip the head detail inference stage for faster processing.
A ComfyUI node for setting image sizes based on the model being used.
Resolution calculator nodes for ComfyUI with model-specific constraints and optimal bucket resolutions
Parameter Overlay, Visual Widgets & Loop nodes for ComfyUI - Display generation parameters on images, true loop without Auto Queue
A very simple and easy to use node to automaticaaly create (square) image crops and masks using YoloV8. This can be very useful when using controlnet and ip adapters
These are just some nodes I wanted and couldn't find where anyone else had made them yet.
An enhanced replacement for the official MiniMax H3 Image Conditioning node in ComfyUI, designed to improve texture quality, fine details, and overall rendering in Text-to-Image (T2I) generation.
This node captures images one at a time from your webcam when you click generate. This is particular useful for img2img or controlnet workflows. NOTE:This node will take over your webcam, so if you have another program using it, you may need to close that program first. Likewise, you may need to close Comfyui or close the workflow to release the webcam.
This ComfyUI node pack allows the user to take a panoramic image and a corresponding depth map, and turn them into a 3D environment, which they can view in an immersive WebXR environment.
Structured MiniMax H3 video prompt compiler: Main and R2V nodes with scenes, characters, camera, timelines, dialogue, sound, and Korean-to-English translation.
A collection of nodes for batch processing texts and images in ComfyUI
ComfyUI nodes for QwenVL (Qwen2.5-VL / Qwen3-VL): image caption, OCR, boxes, video summary.
NODES: DWPose Scaler (Warper), Mouth Mask from Pose (Warper), Facial Part Mask from Pose (Warper), Smart Video Batcher (Warper), Get Batch By Index (Warper), Smart Overlapping Batcher (Warper), Flow Visualizer (Warper), Preprocess for Target (Warper), Crop and Restore (Warper), Aspect Ratio Resolution (Warper)
Various custom nodes for ComfyUI
Advanced real-time control for Z-Image models and Qwen3-4B Text Encoders. These nodes allow you to change your model's weights to boost or lower specific generative phases.
Used to process video redrawing, frame skipping, frame ending early, etc.
A ComfyUI custom node for MiniMax H3 Image And Reference To Video.
Super fast multilingual speech recognition model based on Whisper Large-v3 Turbo. A node for ComfyUI.
This extension for ComfyUI adds a autocompletion feature that helps you write prompts faster and more efficiently. It provides suggestions from premade and custom data files as you type, allowing you to quickly insert and expand predefined keywords.
A simple set of nodes to generate a point cloud from an image and its depth map, perform transformations and some basic operations.
A mixture of effects and quality of life nodes. Nodes: ImageGlitcher (gives an image a cool glitchy effect), ColorStylizer (highlights a single color in an image), QueryLocalLLM (queries a local LLM API though oobabooga), SDXLReslution (resolution picker for the standard SDXL resolutions, the complete list), SDXLResolutionSplit (splits the SDXL resolution into width and height).
A set of ComfyUI nodes to quickly test generated QR codes for scannability. A companion project to ComfyQR.
A collection of custom nodes for ComfyUI designed to apply various image processing effects, stylizations, and analyses.
Use ComfyUI workflows as reusable subworkflows via Subworkflow Input, Subworkflow Output, and Subworkflow nodes
SeedVR2 1.4B image restoration and upscaling for ComfyUI
Experience the CogVideoX model on ComfyUI
Utility nodes for ComfyUI: video saving (H.264/H.265), universal switches, LoRA application, and animated latent preview.
You'll get a new node called SD3 Latent Select Resolution, you can pick the x and y sizes from a list.
Save Image Plus is a custom node for ComfyUI that allows you to save images in JPEG and WEBP formats with optional metadata embedding.
A ComfyUI custom node connecting to local OpenAI-compatible LLM servers (LM Studio or vLLM) that transforms ideas into optimized prompts for various image and video generators.
A collection of custom nodes for ComfyUI that enable powerful batch processing capabilities for both prompts and images.
Haiper API official ComfyUI custom node.
Videos of any length with MiniMax H3: shots on a timeline, characters, voices, songs, storyboard and control videos, rendered part by part in ComfyUI's native loop. Nine example workflows and a guide; the Legacy timeline Director is included. Enhanced fork: per-segment and whole-prompt QwenVL enhancement.
A pair of nodes (Load Image and Save Image) to create a simple loop in your ComfyUI inpainting workflow, without the need of loading your last saved image, and a few others to cut and paste back the cutting into the source.
A wrapper for CraftsMan
ComfyUI custom nodes for Ideogram 4.0 image generation.
Nodes for searching videos by motion
A collection of custom nodes for interacting with ComfyUI's internal HTTP APIs, such as fetching files from workflows.
Advanced multimodal prompt generation nodes for ComfyUI with local GGUF models (Qwen-VL) and cloud API support for vision-based prompt enhancement.
A comprehensive ComfyUI plugin suite that brings professional Photoshop-style layer effects and advanced compositing capabilities. Features modular architecture, 24 blend modes, and enhanced positioning system.
This is set of custom nodes for your ComfyUI local installation. It offers the very basic nodes that are missing in the official 'Vanilla' package. It is a research Node based project on Artificial Intelligence using ComfyUI visual editor. This repository also includes a set of workflows to test the nodes. NOTE:Renamed from 'ComfyUI-Compositing-Nodes-Pack'
This extension node is intended for the use of LCM conversion for SSD-1B-anime. It does not guarantee operation with the original LCM (as it cannot load weights in the current version). To take advantage of fast generation with LCM, a node for using TAESD as a decoder is also provided. This is inspired by ComfyUI-OtherVAEs.
Image processing tool for ComfyUI
Attach a debug node to an output to obtain more detailed information. Uncover the details of your models in ComfyUI with ease.
ComfyUI LC Audio_Video Nodes by lonecatone23 — Create/Save Video, AV pipe, Load Audio cut preview, EQ, volume, channel, separate, VAE Decode wrapper, Get Latent Size. Companion to ComfyUI_LC123_nodes; separate Registry name.
Direct model downloads to your Runod pod with blazing-fast multi-connection support. No more downloading models to your local machine and re-uploading!
Multi-GPU acceleration and caching for MiniMax H3 video generation in ComfyUI: Ulysses sequence and head parallelism across 1-8 GPUs, sparse attention inside the split, a pipelined exchange, and text-encoder/VAE caches.
Aspect ratio selector for ComfyUI based on [a/sd-webui-ar](https://github.com/alemelis/sd-webui-ar?tab=readme-ov-file).
ThoughtBubble is a custom node for ComfyUI that provides an interactive canvas to build and manage your prompts in a more visual and organized way. Think of it as a whiteboard for your ideas, allowing you to link different concepts, create conditional logic, and dynamically generate prompts using a powerful set of commands.
Blender-style Bézier wires for ComfyUI with configurable tension and crossing behavior, plus Shift-drag magnetism to tidy up your graph.
Add a node for drawing text with CR Draw Text of ComfyUI_Comfyroll_CustomNodes to the area of SEGS detected by Ultralytics Detector of ComfyUI-Impact-Pack.
A custom extension for ComfyUI that integrates Photopea directly into the sidebar.
Model-agnostic seamless / tileable image generation for ComfyUI — works on transformer/DiT models (Flux, Wan/Anima) as well as convolutional models (SD1.5, SDXL).
Introduction The ComfyUI_pandai node is a custom ComfyUI node designed to interact with the DeepSeek API. It supports text generation, translation, and text polishing. With this node, users can easily generate text, translate content, and refine the generated text for better quality.
This node uses the Translators library for translation.
This node pack is designed to adjust audio playback speed within ComfyUI, particularly to sync audio with models like FantasyTalking (WAN) that require specific frame rates. It can also be used for general-purpose audio speed control.
Temporally coherent video generation and stylization for ComfyUI using optical flow. Port of SD-CN-Animation to ComfyUI custom nodes.
Fully customizable Classifier Free Guidance for ComfyUI.
A ComfyUI custom node wrapper for Meta's MeshFlow pipeline, providing state-of-the-art artist-like mesh remeshing directly within ComfyUI.
SCAIL and SCAIL-2 pose/mask preprocessing for ComfyUI, including DWPose-compatible pose data, NLF pose renders, condition metadata, and WanVideoWrapper adapter payloads.
Hardened video workflow nodes for ComfyUI with safer output, metadata, and path handling
This repository packages the latest BiRefNet model as a ComfyUI node for use, supporting chunked loading on both CPU and GPU, as well as model caching features.
Compare two images using ComfyUI. Connect images to both image_a and image_b inputs. Press RUN. Then use the slider to compare. Best used when two images are very similar and you want to see the differences very closely. Search for the manager for image compare, or imagecompare.
llama-cpp-python wrapper, with support for vision models. It allows the user to generate text responses from prompts using llama.cpp.
A ComfyUI extension helper for the bult-in Queue Manager that gives you more control over the job queue. You can pause/resume, change the run order, hold individual items, and manually save/load the entire queue to disk for backup that survives a restart/reboot. It also auto-saves/restores the current running queue in case of unintended crashes. This extension does not load any new dependencies.
A complete replacement for rgthree's Power Lora Loader with zero dependencies and two specialized versions to fit any workflow.
Highly customizable Scheduler for ComfyUI.
Face Anonymization make simple and easy.
you can make PBR in comfyUI
Nodes: ComfyUI_ImageToText
Jupyter inside ComfyUI: persistent IPython kernel, in-node notebook cell, and pro external-attach breakpoint.
This node circumnavigates the loss of detail, saturation/desaturation for infinite length video generation, the node bypasses the vae decode and directly patches the latent tensor. experimental covering i2v and vace extend.
Local Hi3D v1.0 workbench and ComfyUI integration
A ComfyUI node for interactively editing sigma schedules via graph and text.
Interactive sigma schedule editor with graph and text input.
Comfy UI nodes for Z-Image-Turbo to run native weights with automatic model downloading and support for 2048x2048 resolution. (Description by CC)
GGUF implementation for the ComfyUI Ultimate SD Upscale node.
Noise, conditioning, and perturbation utility nodes for ComfyUI (procedural noise, mesh drag, latent channel stats preview).
A prompt management plugin for Chinese models like Qwen and Z-Image
Face detection & restoration tools for ComfyUI by Sunx.ai
Audio normalization and enhancement nodes for ComfyUI (LUFS normalization, audio processing utilities).
Enhanced features with flexible choice of inputs and outputs, fine control for pose plotting, freedom to composite poses and fast local pose editting.
A powerful ComfyUI visual processing plugin with multi-modal understanding capabilities, integrating Qwen-VL and SAM2 models
IndexTTS2: A Breakthrough in Emotionally Expressive and Duration-Controlled Auto-Regressive Zero-Shot Text-to-Speech
ComfyUI prompt enhancement / image captioning plugin powered by the Qwen family of large language models.
SongBloom is a music generation plugin for ComfyUI that integrates the entire process of lyrics standardization, model loading, generation, saving, and previewing, and provides DeepSeek V3 assistance for lyric formatting.
A set of custom nodes that simplify things.
Preview and record 3D Gaussian splatting models with interactive 3D rendering and video export. (Description by CC)
Nodes: MergeBlockWeighted
Put unlimited character LoRAs into one image, each locked to its own hand-drawn box — plus reference-image identity lock, cross-region attention dampening, per-region text conditioning, trigger-name auto-activation, and a sparse-token engine that only pays for the tokens that matter.
Analog film-inspired photographic finishing for ComfyUI, featuring 50 deterministic film emulsions, adjustable Emulsion Response, optical effects, film grain, procedural texture, and automatic NVIDIA CUDA acceleration with CPU fallback.
ComfyUI custom nodes for Tencent Youtu-VL vision-language model
For ComfyUI Prompt_Tools
ComfyUI Large Tools
A ComfyUI extension that enables seamless sharing of AI-generated images and videos directly to Discord.
a custom node for [a/Pyramid-Flow](https://github.com/jy0205/Pyramid-Flow)
Progressive one-pass MiniMax H3 video sampling for ComfyUI, jointly using Sol-Attn and combining cross-resolution noise coupling and latent upscaling to address performance bottlenecks and improve generation speed when generating high-resolution, long-form videos with MiniMax H3.
ComfyUI node for Flux Kontext Pro and Max models from Replicate
Custom ComfyUI nodes for ByteDance Lance — a unified 3B multimodal model supporting image and video understanding, generation, and editing in a single framework.