ComfyUI Custom Extensions

Professional motion-compensated temporal video denoising for ComfyUI. Optical flow-based (MEMFOF/RAFT) temporal averaging with independent chroma/luma denoising control.

Interactive 3D scene staging, actor acting, and camera directing suite of custom nodes for ComfyUI.

Advanced color manipulation and image adjustments directly in ComfyUI's latent space

Remove backgrounds from images with [a/BEN](https://huggingface.co/PramaLLC/BEN) in ComfyUI

A comprehensive suite of AI-powered prompt enhancement nodes for ComfyUI using local LLMs (LM Studio or Ollama). Transform simple prompts into detailed, platform-optimized descriptions for video and image generation.

Moondream is a lightweight multimodal large language model. [w/WARN:Additional python code will be downloaded from huggingface and executed. You have to trust this creator if you want to use this node!]

ROCM Optimized Nodes for ComfyUI - High-performance VAE decode and sampling nodes specifically tuned for AMD GPUs with ROCm support, particularly targeting gfx1151 architecture

This is a set of sampling nodes specifically designed for fine-tuning Twinflow models.

Visual studio for composing Ideogram 4 structured JSON box prompts in ComfyUI

Comprehensive ComfyUI nodes for image processing, mask operations, YOLO detection, HDR effects, batch loading and more.

A collection of simple nodes for Frequency Separation / Frequency Recombine with RGB and HSV methods

Automatic AI-powered 3D character rigging inside ComfyUI

A custom node for ComfyUI that adds cinematic and movie scene styles to video generation prompts. This node helps create more dynamic and professional-looking video outputs by incorporating iconic movie scene aesthetics.

Two-finger scrolling (vertical and horizontal) to pan the canvas. Two-finger pinch to zoom in and out. Command-scroll up and down to zoom in and out. Fixes [a/comfyanonymous/ComfyUI#2059](https://github.com/comfyanonymous/ComfyUI/issues/2059).

Custom nodes to process multi exposure images and stack them to produce 32bit exr file with dynamic range data

Load Image thumbnails, delete images, browse input subfolders.

Native Qwen3-VL integration for ComfyUI with image/video analysis and uncensored model support.uilt-in presets for various styles: *Descriptive, Danbooru/e621 tags, Art Critic, Social Media, NSFW,* Batch & Loop Support,Next Scene Generation,JoyCaption Integration

A custom ComfyUI node for testing multiple LoRA models across different strength values. Automatically generates model/clip pairs for each LoRA-strength combination and includes an image saver node with text overlay for easy identification.

Template repository for custom nodes from [ComfyUI-CustomNodes-Template](https://github.com/jhj0517/ComfyUI-CustomNodes-Template).

Endless MiniMax H3 video lip-sync generation with automatic video continuation for ComfyUI, featuring audio chunking, latent context chaining, per-clip prompts, final-frame references, automatic requeueing, and MP4 stitching. Requires the original ComfyUI H3 Motion Context custom node.

Detect human parts using the DeepLabV3+ ResNet50 model from Keras-io. You can extract hair, arms, legs, and other parts with ease and with small memory usage.

Timeline-based director node for MiniMax H3 — visual CUT/segment editor, multi-character reference images, reference video + reference audio (with per-clip audio pairing for lipsync/voice reference), First/Last Frame mode, automatic chunking, two-stage sampling, a VAE re-encode continuity mode that hard-freezes a real re-encoded window of the previous chunk's output across the chunk boundary, and an explicit Seed Hunt on/off switch with a 1-4 candidate count. Bundled with its companion Muse Minimax Refine node — picks one Seed Hunt candidate and continues its sigma schedule at a higher resolution, including full multi-chunk Latent-Only Scouting candidates, not just a single chunk.

Preview and masking tools for ComfyUI: floating popup preview window (multi-monitor, live TAESD preview) and a procedural mask painter that bridges any IMAGE source into the native mask editor.

An unofficial, streamlined, and highly optimized ComfyUI implementation of TeleStyle for video style transfer. (Description by CC)

Adds a gallery to the Load Image node and tabs for Load Checkpoint/Lora/etc nodes

Say goodbye to clutter! 🚀 Integrated Nodes to simplify workflow. 🤖 AI Node: Role-play & rules with one-click presets! 🧠 Programmable Logic: Edit logic in ONE node—no complex wiring! 🌐 Bilaingual: Real-time Chinese/English switching! 📦 SDNQ: Low-VRAM model loader & sampler! ⚡ Versatile cache acceleration node integrating TeaCache and WaveSpeed! 📝Super versatile prompt editor with real-time Danbooru tag lookup! 🔮Exclusive Nunchaku-flux2Klein9b loading node! 🎨 More nodes await! 告别琐碎连线！🚀 多功能集成节点。🤖 AI节点：角色扮演+规则，一键预设！🧠 逻辑计算：一节点搞定运算与比较！🌐 双语：实时中英切换！📦 SDNQ：低显存模型加载与采样！⚡融合了TeaCache和WaveSpeed的多功能缓存加速节点！📝拥有实时查找danbooru提示词的超强万用提示词编辑器！🔮独家的nunchaku-flux2klein9b加载节点！🎨 更多节点等你发现！

Checkpoint and UNET/Diffusion Model loaders for <a href="https://github.com/bitsandbytes-foundation/bitsandbytes">BitsAndBytes</a> NF4 quantized models

Nodes for loading both Checkpoints and UNET/Diffussion models quantized to bitsandbytes NF4 or FP4 format. Still under development and some limitations such as using LoRA might apply still.

Personalize Anything for Free with Diffusion Transformer,use it in comfyUI with wrapper mode

StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation,you can try it in ComfyUI

VantageLongWanVideo is a lightweight project management system for ComfyUI, designed for long-running, prompt-driven video generation. It simplifies workflow management by saving prompts to disk, handling continuity across runs, and allowing resuming or regenerating from any point.

ComfyUI Loop Image is a node package specifically designed for image loop processing. It provides two main processing modes: Batch Image Processing and Single Image Processing, along with supporting image segmentation and merging functions.

Enhanced WanAnimateToVideo with multi-dimensional control

A workflow-compatible NVIDIA RTX Video Super Resolution Pro node for ComfyUI with exact 16K hybrid processing and channel-corruption detection.

Nodes:Openpose Editor Plus

Nodes: DeepFloyd, Filter, Select, Save, Decode, Encode, Repeat, Noise, Noise

A ComfyUI integration for FireRedTTS‑2, a real-time multi-speaker TTS system enabling high-quality, emotionally expressive dialogue and monologue synthesis. Leveraging a streaming architecture and context-aware prosody modeling, it supports natural speaker turns and stable long-form generation, ideal for interactive chat and podcast applications.

A clean, efficient ComfyUI custom node for VoxCPMTTS (Text-to-Speech) functionality. This implementation provides high-quality speech generation and voice cloning capabilities using the VoxCPM model.

A ComfyUI plugin based on HY-Motion 1.0 for text-to-3D human motion generation with custom character support:UE5, MIXAMO, DAZ(G3,G9).

ComfyUI custom node using the fal.ai API for the IC-Light V2 model

Dashboard Nodes for Comfy

ComfyUI-WorkflowGenerator custom nodes for generating ComfyUI workflows from natural language

Heuristic modification of the Heun sampler using a custom function based on normalized distances. For ComfyUI.

Provides the ability to set the temperature for both UNET and CLIP. For ComfyUI.

This custom node package provides nodes specifically for using the mvadapter_ig2mv_sdxl.safetensors adapter within ComfyUI. This adapter is designed for image-guided multi-view generation, typically used for creating textures from 3D mesh renders (position and normal maps).

A Jupyter-style custom node for executing Python code within ComfyUI workflows. Features syntax highlighting, shared variables between cells, and pre-loaded libraries (numpy, torch, PIL, matplotlib).

Nodes to use [a/Smoothed Energy Guidance](https://github.com/SusungHong/SEG-SDXL) for ComfyUI.

ComfyUI-TinyBreaker is a collection of custom nodes specifically designed to generate images using the TinyBreaker model. It's actively developed with ongoing improvements. Although still in progress, these nodes are functional and allow you to explore the potential of the model.

A node for JPEG de-artifacting using [a/FBCNN](https://github.com/jiaxi-jiang/FBCNN).

ComfyUI custom node implementing Florence 2 + Segment Anything Model 2, based on [a/SkalskiP's HuggingFace space](https://huggingface.co/spaces/SkalskiP/florence-sam)

TQ3 KV cache compression for ComfyUI reducing attention KV cache VRAM by ~4.5x using 3-bit Lloyd-Max quantization with Fast Walsh-Hadamard Transform decorrelation.

A custom ComfyUI node designed to create seamless motion effects from single images by integrating with Hunyuan Video through latent space manipulation.

ComfyUI nodes for video object segmentation using [a/SAMURAI](https://github.com/yangchris11/samurai) model.

Implementation of color transfer using KMeans algorithm

一个 ComfyUI 扩展，通过 API 集成实现图像生成及相关功能

A more advanced version of the original ImageScaleToTotalPixels node

A custom node for ComfyUI. It compare two images to rate facial similarity.

音视频、图片、提示词多资源批量管理器，无限分镜流、无限长视频流、无限循环流必备，如需帮助请进Q群：775649071

Pixel art Enhancement Node for ComfyUI

An Unofficial ComfyUI custom node package that integrates [a/Diffusion Self-Distillation (DSD)](https://github.com/primecai/diffusion-self-distillation) for zero-shot customized image generation. DSD is a model for subject-preserving image generation that allows you to create images of a specific subject in novel contexts without per-instance tuning.

ComfyUI Nodes that generate prompts and many more.

Wrapper nodes for OpenDiT: [a/OpenDiT](https://github.com/NUS-HPC-AI-Lab/OpenDiT/), supports Open-Sora t2i and i2i

experimental node pack to test using reference videos for their motion.

Intelligent path organization for ComfyUI. Drag-drop segments, auto-detection (Model, LoRA, Resolution, Seed), template variables, global presets, dual outputs for Image Saver, and 7 beautiful themes. Say goodbye to messy output folders!

A single-purpose, multi-channel curve editor for ComfyUI, providing precise color control over R, G, B, and Luma channels directly within the node graph. It’s a focused, lightweight, and standalone solution built specifically for one task: applying color curves cleanly and efficiently.

Image Adjustments node for ComfyUI with minimal requirements, uses PyTorch for image manipulation operations.

The 'Eses Image Effect Levels' is a ComfyUI custom node that provides a real-time levels adjustment tool directly within the user interface. It allows for interactive control over the tonal range of both images and masks, using a GPU-accelerated PyTorch backend for near instant feedback.

Nodes: Runtime44Upscaler, Runtime44ColorMatch, Runtime44DynamicKSampler, Runtime44ImageOverlay, Runtime44ImageResizer, Runtime44ImageToNoise, Runtime44MaskSampler, Runtime44TiledMaskSampler, Runtime44IterativeUpscaleFactor, Runtime44ImageEnhance, Runtime44FilmGrain

Utilities making it easy to set up inference parameters.

Crosshair guidelines to help align nodes and groups while moving or resizing.

This repository contains ComfyUI custom nodes for StepVideo.

Provide ComfyUI support for FramePack start-and-end image reference

Krea2-focused BBOX canvas, prompt builder, export node, and prompt effect presets for ComfyUI.

Nodes:Conditioning (Blend), Inpainting VAE Encode (WAS), VividSharpen. Experimental nodes, or other random extra helper nodes.

ControlNet for MiniMax-H3. Drive an H3 generation with a depth, canny, pose, HED or MLSD control video, built on ComfyUI's own H3 blocks.

Native ComfyUI MiniMax-H3 exact runtime and composable Sana Sol-Attn integration

Lightweight alignment toolbar for ComfyUI graphs. Provides quick align, equal size, and distribution actions with optional keyboard shortcuts.

This repository provides integration of GPT-4 and Claude 3 models into ComfyUI, allowing for both image and text-based interactions within the ComfyUI workflow.

Attempts to implement [a/CADS](https://arxiv.org/abs/2310.17347) for ComfyUI. Credit also to the [a/A1111 implementation](https://github.com/v0xie/sd-webui-cads/tree/main) that I used as a reference.

It provides the capability to generate CLIP from an image input, unlike unCLIP, which works in all models. (To use this extension, you need to download the required model file from **Install Models**)

Comics/Manga like panel layouts.

Dynamic Node examples for ComfyUI

ComfyUI widget for defining sun light direction for Flux 2 Klein 9B, designed for use with Sun_direction_Lora.

Nodes: MS kosmos-2 Interrogator, Save Image w/o Metadata, Image Scale Bounding Box. An implementation of Microsoft [a/kosmos-2](https://huggingface.co/microsoft/kosmos-2-patch14-224) image to text transformer.

Unofficial implementation of [a/MiniCPM-V](https://github.com/OpenBMB/MiniCPM-V) for ComfyUI

ACE-Step music generation nodes for ComfyUI

ComfyUI adaptation of https://github.com/G-U-N/Motion-I2V

Save a picture as Webp file in Comfy + Workflow loading

PromptTermList (1-6): are some nodes that help with the creation of Prompts inside ComfyUI. Resolution Scale outputs image dimensions using a scale factor. Regex Text Chopper outputs the chopped parts of a text using RegEx.

A semi-random prompt generator for danbooru tags that works alongside your character prompt, allowing you to put your waifu in many scenarios. (for Illustrious/NoobAI/Pony)

ComfyUI implemntation for [a/SyncTalk](https://github.com/ZiqiaoPeng/SyncTalk)

ComfyUI-Qwen-Omni is the first ComfyUI plugin that supports end-to-end multimodal interaction, enabling seamless joint generation and editing of text, images, and audio. Without intermediate steps, with just one operation, the model can simultaneously understand and process multiple input modalities, generating coherent text descriptions and voice outputs, providing an unprecedentedly smooth experience for AI creation.

Local Qwen Image 2.1 prompt rewriting for text-to-image and 1-10 image editing in ComfyUI

A media browser for the ComfyUI sidebar that indexes the images, videos, and audio in your output folders and shows their embedded generation metadata in a searchable panel.

Comprehensive custom nodes for video processing, keyframe management, scene detection, and video analysis in ComfyUI

a comfyui custom node for [a/UniAnimate](https://github.com/ali-vilab/UniAnimate)

a custom node for [a/F5-TTS](https://github.com/SWivid/F5-TTS)

This extension contains a custom node for ComfyUI. The node, called 'Bounding Box Crop', is designed to compute the top-left coordinates of a cropped bounding box based on input coordinates and dimensions of the final cropped image. It does so computing the center of the cropping area and then computing where the top-left coordinates would be.

ComfyUI-Book-Tools is a set o new nodes for ComfyUI that allows users to easily add text overlays to images within their ComfyUI projects. This Node leverages Python Imaging Library (PIL) and PyTorch to dynamically render text on images, supporting a wide range of customization options including font size, alignment, color, and padding. Loop with any parameters (*), prompt batch schedule with prompt selector, end queue for automatic ending current queue.