ComfyUI Custom Extensions
Browse 9,420 ComfyUI extensions and 73,215 custom nodes.
个人零散节点收录,开放给大家用
DreamOmni2中VLM在ComfyUI中的复现,支持int4,int8量化;配合loras可完成原项目的复现
ComfyUI_fnodes is a collection of custom nodes designed for ComfyUI. These nodes provide additional functionality that can enhance your ComfyUI workflows. File manipulation tools, Image resizing tools, IPAdapter tools, Image processing tools, Mask tools, Face analysis tools, Sampler tools, Miscellaneous tools
Experimental BlockCache for ComfyUI's native MOSS-Image Base and SFT.
ComfyUI V3 nodes for MOSS Transcribe Diarize, by T8star-Aix
Native ComfyUI nodes for Zen Image Edit with a single-file Qwen-Image-2.1 checkpoint and student text encoder.
Custom nodes for ComfyUI that allow you to read and write XMP metadata to images
Nodes: HelperNodes_MultilineStringLiteral, HelperNodes_StringLiteral, HelperNodes_Steps, HelperNodes_CfgScale, HelperNodes_WidthHeight, HelperNodes_SchedulerSelector, HelperNodes_SamplerSelector, ...
This custom node extends ComfyUI's image loading functionality with filename output and folder loading capabilities.
Nodes:Prompter, RF Noise, SeedMod.
Nodes: Shadertoy, Load Audio (from Path), Audio Frame Transform (Shadertoy), Audio Frame Transform (Beats)
RTX Video Super Resolution (VSR) batch upscaler with native drag & drop picker, zero-temp-file FFmpeg pipeline, audio copy, auto subfolder and FPS/VFR preservation for ComfyUI
Manual five-color BBOX layout and Character/Object/Text prompt export for MOSS-Image. Reuses the Krea2 BBOX Prompter UI and supports traditional ComfyUI. Requires Krea2 BBOX Prompter Suite to be installed. MIT licensed.
Nodes:ApiRequestNode, LoadVideoNode, JsonParserNode, OllamaRequestNode, OldPhotoColorizationNode, waveform_2_audio, SaveImageUnifiedOutput, VideoHelperUnifiedOutput, ...
SenseNova U1.5 INT8 ConvRot + AEGIS VRAM runtime for ComfyUI
Nodes provide an options to combine prior and decoder models of Kandinsky 2.2.
A comprehensive collection of custom nodes for ComfyUI that provide AI-powered prompt generation tools using Ollama. These nodes help create detailed, professional prompts for text-to-image generation across various domains including character creation, fashion, fantasy scenes, and image analysis.
ComfyUI custom node for loading SVDInt4-quantized Wan/Bernini DiT models.
An extension to ComfyUI that evaluates images using multiple models.
Wan-Video based video generation custom node: seven-mode guidance (CFG/APG/RAAG/S2/Z2/STG_A/STG_R), context-window sampling, and segment prompt-travel.
A ComfyUI custom node implementing AutoGuidance from the paper Guiding a Diffusion Model with a Bad Version of Itself.
Learned MiniMax H3 latent upscaling with integrated low-sigma refinement for ComfyUI.
Native ComfyUI WAN Spectrum forecaster nodes
Extra CFG++ samplers. Works for RF.
This is a custom node designed for ComfyUI that leverages the multimodal large model Doubao from Volcengine Ark to intelligently compare two input images. You can provide two images and a custom text prompt. The node will send this information to the large model and return a detailed textual description of the similarities and differences between the two images.
High-speed and high-accuracy mosaic detection node for ComfyUI. Supports FAST, ACCURATE, and HYBRID modes with ROI refinement.
ComfyUI custom node for directly downloading generated images to your local PC with customizable filenames and formats (PNG/JPEG).
Support adding custom text to the generated images.
A collection of utility / quality-of-life nodes for ComfyUI. Probably only useful to me.
A simple ComfyUI node that let's you use Claude or ChatGPT 4o's VLM capabilities to generate captions/tags for images.
Professional panorama generation tools for ComfyUI converting perspective images/video to equirectangular 360° panoramas with automatic camera calibration via AI, horizon detection, or vertical line detection.
ComfyUI custom nodes for the Netflix VOID video inpainting model (CogVideoX-5B architecture)
In-browser file manager for ComfyUI — browse, preview, upload, rename, move, copy, and trash files in configured roots
Unofficial implementation of siliconflow API for ComfyUI How to use:apply api key in :https://cloud.siliconflow.cn/ add api key in config.json
AWS Rekognition nodes for ComfyUI — compare faces, score image quality, and automatically pick the best image from a batch.
a custom node for [a/JoyHallo](https://github.com/jdh-algo/JoyHallo)
a custom node for [a/ViewCrafter](https://github.com/Drexubery/ViewCrafter)
ComfyUI nodes for Qwen3 TTS Multi character.
Quality-focused Triton W8A8 implicit-GEMM Conv3D acceleration for the Qwen-Image/Wan VAE in ComfyUI, optimized for faster first workflow runs and resolution changes. PuppetVisionAI: https://www.youtube.com/@PuppetVisionAI | LinkedIn: https://www.linkedin.com/in/allen-b-3a35505a/ | Website: https://puppetvision.nl
Selective fused FP8 LingBot-Video Dense 1.3B runtime and workflows for ComfyUI
This node for ComfyUI allows saving images with an optional alpha channel (transparency). It supports saving images in formats like PNG, JPEG, and WebP.
A ComfyUI custom plugin that scans workflows, detects required models, resolves missing metadata, and installs missing assets directly into the correct ComfyUI model folders.
Nodes:MUJinjaRender, MUSimpleWildcard
Professional compositing nodes for ComfyUI - bringing Nuke and Fusion workflows to AI-powered image generation
Node set and workflow to run wan2.1 vace with tiled while keeping temporal and spatial consistency
Sing to Midi 🎶
This plugin is optimized for Fish-Speech-1.5 version and is only applicable to version 1.5
Nodes: Multi Int and Multi Text; allows for the creation of multiple int, floats and string storage and output from a single node.
It’s a custom node that allows you to intuitively toggle prompts ON/OFF and adjust their weights — just like using a checklist.
An implementation of Nari-Labs Dia TTS
Custom nodes for ComfyUI designed for cropping and stitching video frames (image batches). Part of the 'Burgstall Enabling The Awesomeness' suite.
Custom utility nodes for ComfyUI, providing helpers for tasks like video frame manipulation and advanced audio saving. Part of the 'Burgstall Enabling The Awesomeness' suite.
ComfyUI nodes that support video generation by start and end frames
A powerful ComfyUI node for precise control of prompt weights, supporting multiple processing modes and visual weight allocation. (Description by CC)
Search navigation extension.
CoA simple, friendly way to make your ComfyUI job queue survive restarts and crashes.
A custom ComfyUI node for seamless image editing using fal.ai's NanoBanana and Seedream (v4) models. Edit images with AI-powered prompts, supporting multi-image batches, custom resolutions, and easy fal.ai API key integration directly in the node interface.
This ComfyUI node will save images directly to Google Drive by using Google's free API service.
Saves the image in Photoshop format (PSD)
Custom ComfyUI nodes for dynamic CFG control and realism enhancement, originally designed for Anima realism finetunes but works with any diffusion model.
TiledAttentionCouple is a custom node for ComfyUI that enables Attention Coupling across horizontal or vertical tiles. It allows fine(r)-grained control of prompts across different sections of the image. This is especially useful in scenarios where multiple subjects or themes need to coexist in an image without blending them.
Adds 'Assets+' tool to ComfyUI sidebar, which builds upon 'Media Assets' idea albeit expands it to bring Gallery-like experience to Windows machines
Smart Resolution Calculator for ComfyUI - Flexible resolution and latent generation with toggle-based dimension controls. Specify aspect ratio + width OR height to auto-calculate height/width for precise image generation.
Use [a/Doctor Diffusion's snake oil nLoRAs](https://civitai.com/models/987843) as well as [a/other negative LoRAs](https://civitai.com/models/186617/doctor-diffusions-negative-xl-lora) easily within ComfyUI.
An extended Load Video node with an aspect-ratio-locked, WYSIWYG crop rectangle that outputs the cropped VIDEO.
Save image like the native node in ComfyUI but without metadata, supporting filename_prefix with variables like %date:yyyy-MM-dd_hh-mm-ss%, %date:yy-M-d_h-m-s% and %KSampler.seed% to include values from nodes
ComfyUI custom nodes for GGUF LLM model inference with chat support, conversation history, session management, and GPU layer offloading.
A custom ComfyUI node that draws parametric facial masks with black lines on white or transparent backgrounds. (Description by CC)
A custom ComfyUI node for audio enhancement using Resemble AI's Resemble Enhance model. Created using OpenHands, Cline, and DeepSeek.
ComfyUI-Lumina-mGPT-Wrapper is a custom node for ComfyUI that integrates the advanced Lumina-mGPT model. It offers high-quality image generation with support for multiple model sizes and advanced features.
[a/sd-webui-pixelart](https://github.com/mrreplicart/sd-webui-pixelart) are referenced by many webui users, this node is mean to use it in ComfyUI.
Manipulation nodes for Image, Latent
ComfyUI ElevenLabs TTS Node - Text-to-speech integration with advanced voice controls
A general-purpose, dependency-free File and Folder Browser API for ComfyUI custom nodes.
Native ComfyUI port of kijai's WanVideo-Wrapper TimeToMove for video generation, currently supporting LCM sampler with frame generation capabilities. (Description by CC)
Lightweight OpenAI-compatible LLM nodes for ComfyUI, with LM Studio, Ollama, Responses API, image input, MCP tools, and local MCP runners.
A UI extension that shows a preview popup of the model's cover image when you hover over a model name in loaders (Checkpoint, LoRA, UNET, etc.).
Add a button that formats the workflow graph
The ultimate Image Manager & Gallery for ComfyUI. Automatically catalog generations, track lineage, and restore workflows with a single click.
NODES:Batch Image Blend, Mask Levels Adjust, Get Batch Count, Load Lora Name, Load Sampler Name, Load Scheduler Name, Load Ckpt Name.... The nodes in this repository are only used as secondary nodes.
Turn any image into clean, grid-aligned pixel art inside ComfyUI, using the compiled SpriteFusion Pixel Snapper engine — plus color controls, classic video-game palettes, a pixel-perfect resizer, and an interactive preview with a magnifier.
Batch folder processing nodes for ComfyUI — iterate a folder of images or videos through any workflow. Load sequentially, extract video frames, save text outputs, auto-loop with one click. Resume interrupted batches instantly.
ComfyUI extension that adds a glowing visual effect to nodes during execution for enhanced visual feedback.
Sony Woosh audio generation custom node for generating immersive sound effects from text and video. (Description by CC)
A comprehensive suite of ComfyUI custom nodes for image processing, prompt verification, comparison, extraction, occlusion masking, batch loading, and advanced saving.
Custom node to pause a string flow/prompt and let you edit the text
A powerful drawing and annotation tool for ComfyUI that lets you add notes, sketches, and annotations directly on your workflow canvas with full layer support.
A ComfyUI custom node implementing Colored Noise Sampling (CNS)—a plug-and-play SDE sampler that actively exploits the spectral bias of diffusion models to improve image quality.
Automatically detects, downloads, and routes missing workflow models into the correct ComfyUI model directories.
Advanced color manipulation and image processing nodes for ComfyUI: color extraction, contrast analysis, gradient generation, and image layout.
Advanced ComfyUI node for video generation workflows that uses multimodal LLMs to analyze start and end frames, generating high-quality video prompts with cinematic descriptions of camera movement, lighting transitions, and environmental atmosphere in English and Chinese. (Description by CC)
A node that lets you save and reuse parts of prompts (embeddings, quality keywords, and so on.)
ComfyUI nodes for generating and editing speech from SRT subtitle files using VoxCPM text-to-speech model, supporting multi-speaker dialogue and audio replacement workflows.
String utility for ComfyUI
ComfyUI-Meshy is a 3D generation extension based on Meshy AI API. It provides Text-to-3D and Image-to-3D capabilities within ComfyUI, allowing you to generate 3D models directly from text prompts or images. Supports multiple AI models (Meshy-4, Meshy-5, Meshy-6) with customizable topology, polygon count, and PBR settings.
Grid/gallery-based style selector for ComfyUI. Browse and apply prompt styles from a searchable visual card grid.
Use [a/Pilgram2](https://github.com/mgineer85/pilgram2) filters in ComfyUI
A custom node to support and load OFTv2 adapters
A set of Custom Nodes for Compositing for ComfyUI