ComfyUI Custom Extensions
Browse 9,420 ComfyUI extensions and 73,215 custom nodes.
ComfyUI nodes for Echo-Memory: controlled memory study on Wan 2.1 1.3B (Context, Compression, Spatial, State-Space).
A flexible and customizable prompt generator for generating detailed and creative prompts for image generation models for ComfyUI
Nodes:3D Pose Editor
Nodes for loading and using VAEs in ways not supported by base ComfyUI. Currently supports Wan upscale VAE, more may be added later as needed.
This project provides a Tensorrt implementation for fast image upscaling inside ComfyUI (3-4x faster)
ComfyUI [a/AniPortrait](https://github.com/Zejun-Yang/AniPortrait)
Training-free Krea2 style reference nodes for ComfyUI, with LoRA-like single-image transfer, experimental two-reference blending, low content leakage, and preserved image quality.
Identity preservation, latent anchoring, upscale-pass quality, and STG guidance nodes for the LTX2 video diffusion model
FreeFuse: compose multi-subject LoRAs for FLUX, Z-Image, Klein, SDXL, Krea2, MOSS Image, Anima and native MiniMax H3 video. Upgrade to v1.0.14+ for GGUF tensor-format fixes.
A custom node for ComfyUI to integrate Google Gemini API.
The implementation of MiniCPM-V-4_5 has been seamlessly integrated into the ComfyUI platform, enabling the support for text-based queries, video queries, single-image queries, and multi-image queries to generate captions or responses.
These nodes are made to support 'Mixture of Expert' Flow models with the architecture of Wan2.2 A14B (With a high noise expert and low noise expert). Instead of guessing the denoising step at which to swap from tyhe high noise model to the low noise model, this node automatically chanage to the low noise model when we reach the diffusion timestep at which the signal to noise ratio is supposed to be 1:1.
An implementation for InfiniteYou
Qwen Image Integrated KSampler - Github: https://github.com/luguoli - intelligent multimodal sampler, support Z-Image, optimizes official offset issues, image scaling, multiple reference images, automatic VRAM/RAM management, batch generation, automatic saving, sound notification
The iTools are some quality of life nodes, like read a possible prompt used to create an image, save a prompt to file as a new line, read prompts from a multiline file.
A collections of nodes to support GLSL shaders inside a workflow. Provides nodes: glslViewer, glslEditor, glslEditorPro, int, float, vec2, vec3 and vec4.
Radiance is a 32-bit color space collection of nodes for ComfyUI.
Font Animation, Speech Recognition, Caption Generator, TTS
VDN-H3 (Video Delta Net) hybrid attention for MiniMax-H3
Voice Clone and TTS model.
NODES: Add Mask For IC Lora, Create Context Window, Concatenate Context Window, Auto Patch
dapaoAPI 是一套为 ComfyUI 设计的高质量自定义节点集合,提供从图像生成、图像分析到文本处理的完整工作流支持。
A simple password to protect ComfyUI.
You can InstantIR to Fix blurry photos in ComfyUI ,[a/InstantIR](https://github.com/instantX-research/InstantIR):Blind Image Restoration with Instant Generative Reference
This repo creates a series of nodes that enable you to utilize the [a/Griptape Python Framework](https://github.com/griptape-ai/griptape/) with ComfyUI, integrating AI into your workflow. This repo creates a series of nodes that enable you to utilize the Griptape Python Framework with ComfyUI, integrating AI into your workflow.
A massive node pack consisting of over 200 nodes, including image processing, masking, text handling, and arithmetic operations. NOTE: A replacement node pack provided for existing users following the retirement of the original author of the widely used WAS Node Suite.
A suite of custom nodes for ConfyUI that includes GPT text-prompt generation, LoadVideo,SaveVideo,LoadFramesFromFolder and FrameInterpolator
Nodes: ColorBlend, ControlLoraSave, GetImageSize. NOTE: Control-LoRA recolor example uses these nodes.
ComfyUI- CCSR upscaler node
Set of custom nodes to use with the ComfyUI Flux Continuum: Modular Interface. NODES: Text Versions, Image64 Display, Tabs, Step Slider, Denoise Slider, Guidance Slider, Batch Slider, Max Shift Slider, ControlNet Slider and more
Modern OpenPose pose editor for ComfyUI with collections, JSON import/export, background image support, and compatibility with legacy pose JSON.
YuE2 music generation, piano roll editing, and joint AR/NAR LoRA training for ComfyUI
There are many very practical nodes, mainly related to images, masks, text, integers, and LoRa. English users need to download the additional translation patch: https://github.com/zml-w/ZZZ_ZML_English_Patch
Build a person once, then shoot a whole series: framing, pose, placement, expression and aspect ratio vary while the person stays the same.
Face Detailer is a custom node for the 'ComfyUI' framework inspired by !After Detailer extension from auto1111, it allows you to detect faces using Mediapipe and YOLOv8n to create masks for the detected faces.
A powerful anti-burn allowing much higher CFG scales for latent diffusion models (for ComfyUI)
Implementation of PMRF on ComfyUI
A ComfyUI extension for controlling and managing node group execution flow. Features include single/multiple group execution, delay control, signal chaining, and execution list repetition processing.
Implementation of UltraPixel on ComfyUI
MCP server + embedded terminal that lets Claude Code see and edit your ComfyUI workflows
Nodes: JWInteger, JWFloat, JWString, JWImageLoadRGB, JWImageResize, ...
Custom nodes use gigapixelai in comfyui.
Nodes:segformer_clothes, segformer_agnostic, segformer_remove_bg, stabel_vition. Nodes for model dress up.
An extension to ComfyUI that introduces logic nodes and conditional rendering capabilities.
ComfyUI nodes and workflows for MiniMax H3 image generation and editing.
Korean-friendly practical custom nodes for ComfyUI
ComfyUI custom node for ControlNet-LLLite for Anima (DiT-based).
libigl geometry processing wrapper for ComfyUI - mesh manipulation and analysis nodes
DaSiWa Custom Nodes Collection
Veda learned sparse attention for MiniMax-H3 in ComfyUI: ~2-3x faster T2VA / FL2VA / R2VA video+audio generation, LoRA-compatible. NVIDIA (Triton INT8, SM80 and newer, Linux / Windows) and Apple silicon (MLX).
ComfyUI custom nodes for TencentARC Pixal3D image-to-3D generation with GLB export, FlashAttention 2/3 selection, and ComfyUI DynamicVRAM/Aimdo integration
ComfyUI MiniMax H3 native masked AV continuation and streaming suite for long video generation.
fastblend for comfyui, and other nodes that I write for video2video. rebatch image, my openpose
Custom nodes for using fal API. Video generation with Kling, Runway, Luma. Image generation with Flux. LLMs and VLMs OpenAI, Claude, Llama and Gemini.
ComfyUI Unique3D is custom nodes that running AiuniAI/Unique3D into ComfyUI[w/Please follow readme to install with ComfyUI embedded python.]
adapted from [a/https://github.com/balazik/ComfyUI-PuLID-Flux](https://github.com/balazik/ComfyUI-PuLID-Flux). common fusion methods for multi-image input, some further experimental fusion methods, switch between using gray image (official) and rgb.,
The ode v2 version is a creative sampler characterized by low contrast, near-realistic quality, and artistic creation. It can only be used with high noise for 6 steps, low noise for 2 steps, and a middle split step of 4 steps. It requires a unique LoRA, which is currently in training and undergoing refinement, and is only in the testing phase. This version offers multiple options for you to choose from, and my recommendation is to go with robust-smooth or even lower. Stay tuned for the official release.
Nodes: LLLiteLoader
A minimalistic implementation of [a/Robust Video Matting (RVM)](https://github.com/PeterL1n/RobustVideoMatting/) in ComfyUI
СomfyUI version of [a/Euler Smea Dyn Sampler](https://github.com/Koishi-Star/Euler-Smea-Dyn-Sampler). It adds samplers directly to KSampler nodes.
Blender plugin to send requests to a ComfyUI server.
Accelerate FLUX inferencing speed for ComfyUI.
Inspired by [a/InstantID](https://github.com/instantX-research/InstantID) and [a/InstantID Comfy](https://github.com/cubiq/ComfyUI_InstantID) This ZenID Node has been refactored for specialized tasks like Face Swap
a node for comfyui for restore/edit/enchance faces utilizing face recognition
This is a ComfyUI plugin that integrated OpenCut into ComfyUI, originally developed by [a/OpenCut](https://github.com/OpenCut-app/OpenCut)
Custom ComfyUI nodes providing unified image and mask resizing with multiple scaling modes, aspect-ratio preservation, center crop alignment, and stable tensor-based mask transformations.
Easily use Magic Animate within ComfyUI! [w/WARN: This extension requires 15GB disk space.]
A simple implementation of real-time 3D lighting in ComfyUI. It's an open-source node, have fun playing around!
[a/Clarity AI](https://clarityai.cc) is a creative image enhancer and is able to upscale to high resolution. [w/NOTE: This is a Magnific AI alternative for ComfyUI.] Create an API key on [a/ClarityAI.cc/api](https://clarityai.cc/api) and add to environment variable 'CAI_API_KEY' Alternatively you can write your API key to file 'cai_platform_key.txt' You can also use and/or override the above by entering your API key in the 'api_key_override' field of the node.
Nodes:HDR Effects (SuperBeasts.AI). This repository contains custom nodes for ComfyUI created and used by SuperBeasts.AI (@SuperBeasts.AI on Instagram)
This project addresses the issue of numerous hand defects in AI-generated portrait images by using a workflow based on FLUX/FLUX-Fill to correct hand deformities. It is effective for both real-life and anime images, including those generated by DiT/SDXL/Midjourney. It supports diffusers, gradio, ComfyUI, and more
QWen-VL-Plus & QWen-VL-Max in ComfyUI
Slice regions of the canvas and convert them to masks for regional conditions widh PNG preview output. And a few support nodes.
Manage models: browsing, download and delete.
Manage models: browsing, download and delete.
ComfyUI nodes for automatically generating XML-style prompts compatible with NewBie models using LLM APIs, with style customization and preset management capabilities. (Description by CC)
This extension automates the creation of structured XML prompts for the NewBie model by using LLM APIs to transform natural language or images into formatted descriptions. It provides specialized nodes for high-robustness prompt generation and seamless artistic style injection to enhance image generation workflows.该插件利用大语言模型 API 将自然语言或图片自动转化为适用于 NewBie 模型的结构化 XML 提示词。通过提供高度健壮的提示词生成与画面风格注入节点,它显著提升了图像生成流程的效率与效果。
A comprehensive toolkit for standardizing, packaging and deploying ComfyUI workflows as reproducible environments and production-ready REST services
Luma Dream Machine API official ComfyUI custom node.
ComfyUI custom node for TurboDiffusion I2V (Image-to-Video) generation with dual-expert sampling and SLA attention optimization.
Comfy-Topaz is a custom node for ComfyUI, which integrates with Topaz Photo AI to enhance (upscale, sharpen, denoise, etc.) images, allowing this traditionally asynchronous step to become a part of ComfyUI workflows. NOTE:Licensed installation of Topaz Photo AI
A set of custom ComfyUI nodes for performing basic post-processing effects including Film Grain and Vignette. These effects can help to take the edge off AI imagery and make them feel more natural.
Memory-efficient image upscaling using SeedVR2 models with advanced tiling and detail-preserving stitching. Supports both stable and nightly SeedVR2 builds (3B/7B, FP16/FP8, GGUF models). Requires ComfyUI-SeedVR2_VideoUpscaler to be installed.
StringOps is a versatile text processing toolkit built for ComfyUI's node-based workflows
Wrapped Joy Caption alpha 2 node for comfyui from [a/https://huggingface.co/spaces/fancyfeast/joy-caption-alpha-two](https://huggingface.co/spaces/fancyfeast/joy-caption-alpha-two) Easy use, for GPU with less 19G, please use nf4 for better balanced speed and result. This Node also took a reference from /chflame163/ComfyUI_LayerStyle and [a/https://huggingface.co/John6666/joy-caption-alpha-two-cli-mod](https://huggingface.co/John6666/joy-caption-alpha-two-cli-mod)
A browser panel for the chores around ComfyUI (adds no nodes). Models: scan for Civitai covers, trigger words and base models. Model Check: when a workflow opens, it finds missing models and puts in the same file even if it was renamed or moved. Gallery: search outputs by prompt or LoRA, drag an image back to restore its workflow. Keep whole workflows, or combos (main model + LoRAs + prompt) that lay out a wired group on the canvas. Edit prompts as tags; non-English input becomes English. Activity log with undo. Character voices with the companion Anomalous TTS node.
Lightweight ComfyUI wrapper for IndexTTS 2 (voice cloning + emotion control).
Lightweight and Efficient, 🎧Ultra High-Quality Voice Cloning, Chinese and English.
A ComfyUI custom node that adds diversity to Z-Image Turbo outputs by adding random noise to text prompt embeddings to compensate for low seed variance. (Description by CC)
Quality of Life Nodes from ControlAltAI. Flux Resolution Calculator, Flux Sampler, Flux Union ControlNet Apply, Noise Plus Blend, Boolean Logic, and Flux Region Nodes.
Implementation of MDM, MotionDiffuse and ReMoDiffuse into ComfyUI.
ComfyUI custom nodes to create output lists with strings and numbers, make combinations of them, and help with XYZ-Gridplots
This node pack provides the official ComfyUI workflow for ICEdit.
Nodes: Run python tools/download_weights.py first to download weights automatically
This extension extends ComfyUI's capabilities with respect to manipulating conditionings.
This tool provides a viewer node that allows for checking multiple outputs in a grid, similar to the X/Y Plot extension.
Run [a/Replicate models](https://replicate.com/explore) in ComfyUI.
Based on [a/https://github.com/apple/ml-depth-pro](https://github.com/apple/ml-depth-pro)
VoxCPM2 TTS for ComfyUI. 30 languages, voice design, controllable cloning, 48kHz audio, and LoRA training
Nodes:Phi3mini_4k_ModelLoader_Zho, Phi3mini_4k_Zho, Phi3mini_4k_Chat_Zho